how to use ai for assignments

Microsoft 365 Life Hacks > Writing > Is it OK to use AI on your school assignments?

Is it OK to use AI on your school assignments?

Artificial intelligence has been an impactful tool in every field, from creative pursuits to engineering and technical industries. AI-powered tools that can write and produce with simple prompts have been used to create paintings, write essays and poems, generate ideas for content, and streamline complex processes to make it easy for people to stay productive.

It’s no wonder that AI has been involved with education at all levels, from universities and advanced degrees to the elementary school level. Students are using AI for homework assignments, especially for essay writing.

While this may seem like an efficient way to finish schoolwork, a reliance on AI can hurt a student’s integrity and prevent any actual learning from occurring. It’s important to understand how AI writing works , how to use AI in your homework assignments, and how to avoid serious issues, such as plagiarism and cheating.

Write with Confidence using Editor

Elevate your writing with real-time, intelligent assistance

How AI can help with school assignments

AI is especially effective at generating ideas and launching points for essays, art classes, and assignments. By making a list of keywords and context for an assignment, then entering them into generative AI, students can brainstorm ideas and areas of research to focus on.

For example, if you’re writing a book report , you can use AI to suggest thematic elements that are crucial to the story. And by placing a classic work in its historical context, AI can summarize important topics of research that you can incorporate in your work.

Students can also use AI to understand the nuances of grammar and sentence structure, especially those whose native language isn’t English.

When is AI considered a step too far?

When students rely entirely on AI to complete their school assignments, they are effectively cheating in their classes as well as cheating themselves. Students may fail to learn the material, which can impact future lessons and exams, as well as placement in advanced classes in the years to come.

And by not learning on their own, they might be lost when it comes time to applying these lessons in the real world. By not understanding the essentials of writing , for example, students might struggle during internships or fall short of their career goals at a critical stage of their post-graduate lives.

AI can also be prone to make obvious or glaring errors in its output. Since generative AI is still in its nascent stages of development, it can misinterpret a prompt, offer incorrect or outdated information, or fail to meet up to standards of expertise, authoritativeness, and trustworthiness—three elements that are critical for academic writing.

Finally, by learning the ins and outs of essay writing, students develop rhetorical strategies , argumentative and persuasive skills , and critical thinking —all while developing their own unique voice.

How using AI can backfire

Like any useful tool, misusing it can cause more problems than it solves. Here are some ways that AI can hurt instead of help students:

• Plagiarism. This is a violation of integrity that can cause a student to fail an assignment in an academic setting, disrupting the trust between the educator and the student. In a real-world context, journalists who have been found plagiarizing stories have faced consequences such as job loss and reputational hits.
• AI detection. Tools have been created to detect when text has been generated by AI. Since generative AI operates by paraphrasing real-world text, AI detectors can notice patterns in text and alert a user to copyright infringement or cyber compliance. Teachers will likely frown on assignments written with large amounts of AI input.
• Red flags. Experienced teachers can detect signs of AI generation in assignments. According to some educators, some tip-offs to AI-generated content might include perfect grammar, bland writing style, and failing to respond to the actual writing prompt. Essays that markedly improve in such a short time might be seen as suspicious.

Ultimately, AI is a tool best used for generating ideas instead of being used to complete entire assignments. Learn more about how to get the most out of AI technology with other life hacks ,and explore tips for getting the most out of your writing.

Get started with Microsoft 365

It’s the Office you know, plus the tools to help you work better together, so you can get more done—anytime, anywhere.

Topics in this article

More articles like this one.

What is independent publishing?

Avoid the hassle of shopping your book around to publishing houses. Publish your book independently and understand the benefits it provides for your as an author.

What are literary tropes?

Engage your audience with literary tropes. Learn about different types of literary tropes, like metaphors and oxymorons, to elevate your writing.

What are genre tropes?

Your favorite genres are filled with unifying tropes that can define them or are meant to be subverted.

What is literary fiction?

Define literary fiction and learn what sets it apart from genre fiction.

Everything you need to achieve more in less time

Get powerful productivity and security apps with Microsoft 365

Explore Other Categories

• Enroll & Pay
• New Faculty

Using AI ethically in writing assignments

The use of generative artificial intelligence in writing isn’t an either/or proposition. Rather, think of a continuum in which AI can be used at nearly any point to inspire, ideate, structure, and format writing. It can also help with research, feedback, summarization, and creation. You may also choose not to use any AI tools. This handout is intended to help you decide.

A starting point

Many instructors fear that students will use chatbots to complete assignments, bypassing the thinking and intellectual struggle involved in shaping and refining ideas and arguments. That’s a valid concern, and it offers a starting point for discussion:

Turning in unedited AI-generated work as one’s own creation is academic misconduct .

Most instructors agree on that point.  After that, the view of AI becomes murkier. AI is already ubiquitous, and its integrations and abilities will only grow in the coming years. Students in grade school and high school are also using generative AI, and those students will arrive at college with expectations to do the same. So how do we respond?

Writing as process and product

We often think of writing as a product that demonstrates students’ understanding and abilities. It can serve that role, especially in upper-level classes. In most classes, though, we don’t expect perfection. Rather, we want students to learn the process of writing. Even as students gain experience and our expectations for writing quality rise, we don’t expect them to work in a vacuum. They receive feedback from instructors, classmates, friends, and others. They get help from the writing center. They work with librarians. They integrate the style and thinking of sources they draw on. That’s important because thinking about writing as a process involving many types of collaboration helps us consider how generative AI might fit in.   

Generative AI as a writing assistant

We think students can learn to use generative AI effectively and ethically. Again, rather than thinking of writing as an isolated activity, think of it as a process that engages sources, ideas, tools, data, and other people in various ways. Generative AI is simply another point of engagement in that process. Here’s what that might look like at various points:

Early in the process

• Generating ideas . Most students struggle to identify appropriate topics for their writing. Generative AI can offer ideas and provide feedback on students’ ideas.  
• Narrowing the scope of a topic . Most ideas start off too broad, and students often need help in narrowing the scope of writing projects. Instructors and peers already do that. Generative AI becomes just another voice in that process.
• Finding initial sources . Bing and Bard can help students find sources early in the writing process. Specialty tools like Semantic Scholar, Elicit, Prophy, and Dimensions can provide more focused searches, depending on the topic.
• Finding connections among ideas . Research Rabbit, Aria (a plug-in for Zotero) and similar tools can create concept maps of literature, showing how ideas and research are connected. Elicit identifies patterns across papers and points to related research. ChatGPT Pro can also find patterns in written work. When used with a plugin, it can also create word clouds and other visualizations.
• Gathering and formatting references . Software like EndNote and Zotero allow students to store and organize sources. They also save time by formatting sources in whatever style the writer needs.
• Summarizing others’ work . ChatGPT, Bing and specialty AI tools like Elicit do a good job of summarizing research papers and webpages, helping students decide whether a source is worth additional time.
• Interrogating research papers or websites . This is a new approach AI has made possible. An AI tool analyzes a paper (often a PDF) or a website. Then researchers can then ask questions about the content, ideas, approach, or other aspects of a work. Some tools can also provide additional sources related to a paper.
• Analyzing data . Many of the same tools that can summarize digital writing can also create narratives from data, offering new ways of bringing data into written work.
• Finding hidden patterns . Students can have an AI tool analyze their notes or ideas for research, asking it to identify patterns, connections, or structure they might not have seen on their own.
• Outlining . ChatGPT, Bing and other tools do an excellent job of outlining potential articles or papers. That can help students organize their thoughts throughout the research and writing process. Each area of an outline provides another entry point for diving deeper into ideas and potential writing topics.
• Creating an introduction . Many writers struggle with opening sentences or paragraphs. Generative AI can provide a draft of any part of a paper, giving students a boost as they bring their ideas together.

Deeper into the process

• Thinking critically . Creating good prompts for generative AI involves considerable critical thinking. This isn’t a process of asking a single question and receiving perfectly written work. It involves trial and error, clarification and repeated follow-ups. Even after that, students will need to edit, add sources, and check the work for AI-generated fabrication or errors.
• Creating titles or section headers for papers . This is an important but often overlooked part of the writing process, and the headings that generative AI produces can help students spot potential problems in focus.
• Helping with transitions and endings . These are areas where students often struggle or get stuck, just as they do with openings.
• Getting feedback on details . Students might ask an AI tool to provide advice on improving the structure, flow, grammar, and other elements of a paper.
• Getting feedback on a draft . Instructors already provide feedback on drafts of assignments and often have students work with peers to do the same. Students may also seek the help of the writing center or friends. Generative AI can also provide feedback, helping students think through large and small elements of a paper. We don’t see that as a substitute for any other part of the writing process. Rather, it is an addition.

Generative AI has many weaknesses. It is programmed to generate answers whether it has appropriate answers or not. Students can’t blame AI for errors, and they are still accountable for everything they turn in. Instructors need to help them understand both the strengths and the weaknesses of using generative AI, including the importance of checking all details.

A range of AI use

Better understanding of the AI continuum provides important context, but it doesn’t address a question most instructors are asking: How much is too much ? There’s no easy answer to that. Different disciplines may approach the use of generative AI in very different ways. Similarly, instructors may set different boundaries for different types of assignments or levels of students. Here are some ways to think through an approach:

• Discuss ethics . What are the ethical foundations of your field? What principles should guide students? Do students know and understand those principles? What happens to professionals who violate those principles?
• Be honest . Most professions, including academia, are trying to work through the very issues instructors are. We are all experimenting and trying to define boundaries even as the tools and circumstances change. Students need to understand those challenges. We should also bring students into conversations about appropriate use of generative AI. Many of them have more experience with AI than instructors do, and adding their voices to discussions will make it more likely that students will follow whatever guidelines we set.  
• Set boundaries . You may ask students to avoid, for instance, AI for creating particular assignments or for generating complete drafts of assignments. (Again, this may vary by discipline.) Just make sure students understand why you want them to avoid AI use and how forgoing AI assistance will help them develop skills they need to succeed in future classes and in the professional world.
• Review your assignments . If AI can easily complete them, students may not see the value or purpose. How can you make assignments more authentic, focusing on real-world problems and issues students are likely to see in the workplace?
• Scaffold assignments . Having students create assignments in smaller increments reduces pressure and leads to better overall work.
• Include reflection . Have students think of AI as a method and have them reflect on their use of AI. This might be a paragraph or two at the end of a written assignment in which they explain what AI tools they have used, how they have used those tools, and what AI ultimately contributed to their written work. Also have them reflect on the quality of the material AI provided and on what they learned from using the AI tools. This type of reflection helps students develop metacognitive skills (thinking about their own thinking). It also provides important information to instructors about how students are approaching assignments and what additional revisions they might need to make.
• Engage with the Writing Center, KU Libraries , and other campus services about AI, information literacy, and the writing process. Talk with colleagues and watch for advice from disciplinary societies. This isn’t something you have to approach alone.

Generative AI is evolving rapidly. Large numbers of tools have incorporated it, and new tools are proliferating. Step back and consider how AI has already become part of academic life:  

• AI-augmented tools like spell-check and auto-correct brought grumbles, but there was no panic.
• Grammar checkers followed, offering advice on word choice, sentence construction, and other aspects of writing. Again, few people complained.
• Citation software has evolved along with word-processing programs, easing the collection, organization, and formatting of sources.
• Search engines used AI long before generative AI burst into the public consciousness.

As novel as generative AI may seem, it offers nothing new in the way of cheating. Students could already buy papers on the internet, copy and paste from an online site, have someone else create a paper for them, or tweak a paper from the files of a fraternity or a sorority. So AI isn’t the problem. AI has simply forced instructors to deal with long-known issues in academic structure, grading, distrust, and purpose. That is beyond the scope of this handout, other than some final questions for thought:

Why are we so suspicious of student intentions? And how can we create an academic climate that values learning and honesty?

Center for Teaching Innovation

Ai in assignment design.

Using generative artificial intelligence (AI) can be both productive and limiting—it can help students to create and revise content, yet it also has the potential to undermine the process by which students create. When incorporated effectively into assignments, generative AI can be leveraged to stimulate students' ability to apply essential knowledge and develop critical thinking skills. 

As you explore the possible uses of generative AI in your course, note that establishing a general familiarity with generative AI and being mindful of accessibility and ethical concerns will be helpful. 

The following process may help you determine how to best incorporate generative AI into your course assignments.

Affirm What You Actually Want to Assess

As you decide how you might incorporate AI into your course, it’s important to revisit your current course assessment plan, most importantly your course learning outcomes —that is, the skills and knowledge you want students to learn and demonstrate by the end of your course. Once you have a clear idea of the specific skills/knowledge you want to assess, the following questions can help determine whether or not your current assignments are effective and assessing what you want them to assess:

• Does my assignment call for the same type of thinking skills that are articulated in my class outcomes? For example, if my course learning outcome calls for students to analyze major themes in a work, is there risk of my final assignment prompting students to do more (e.g., synthesize multiple themes across multiple works) or to do less (e.g., merely identify a theme) than this outcome? If so, there may be a misalignment that can easily be addressed.
• Does my assignment call for the same type of thinking skills that students have actually practiced in class? For example, if I am asking students to generate a research prospectus, have I given them adequate opportunity to develop—and receive feedback on—this skill in class?
• Depending on your discipline, is there a need for an additional course outcome that honors what students now need to know about the use of generative AI in your course/field?

Explore When & How Generative AI Can Facilitate Student Learning

Once you have affirmed your learning outcomes and ensured that your assignments are properly aligned with those outcomes, think about if, when, and how it might make sense to incorporate generative AI. Is there a way to leverage generative AI to engage students in deeper learning, provide meaningful practice, or help scaffold your assignments?

Consider the usefulness of generative AI to serve as:

• Have students analyze AI-generated texts to articulate what constitutes “good” (and not so good) responses to prompts.
• Have students analyze AI-generated texts and engage in error analysis to develop more nuanced and discipline-specific writing skills.
• Leverage the use of generative AI platforms to help students become more discerning. This can help students develop the critical thinking and information literacy skills required to effectively and responsibly use such platforms.
• Have students revise AI-generated texts to develop critical thinking skills.
• Have students engage with a generative AI platform as a tutor. 
• Facilitate students’ responsible, self-guided use of generative AI to develop select discipline specific skills (e.g., coding in computer science courses)
• Have students use generative AI to off-load repetitive tasks.
• Have students use generative AI to conduct preliminary analysis of data sets to confirm broad takeaways and affirm that their more nuanced analysis is heading in the right direction.

Identify When Generative AI Cannot Facilitate Student Learning

It is often the case that students cannot—or should not—leverage generative AI to promote or demonstrate their own learning. To help ensure that your assignment design highlights students’ unique perspectives and underscores the importance of a (non-generative AI informed) discipline-specific process, consider how to emphasize metacognition, authentic application, thematic connection, or personal reflection.  

Even if another part of an assignment calls for the use of generative AI, the following strategies may supplement the uses of AI highlighted above and foster deep and meaningful learning:

• Have students identify the successes and challenges they experienced throughout the completion of a project.
• Have students set incremental goals throughout a project, highlighting next steps of a discipline-specific process, resources they used, and the steps about which they are enthusiastic/nervous.
• Have students self-assess their work, identifying strengths and weaknesses of their product/effort.
• Have students engage in problem-based learning projects, ideally in authentic settings (e.g., problems that focus on our local community, real-world challenges, real-world industries, etc.).
• Have students present projects (and engage with) authentic audiences (e.g., real stakeholders, discipline-specific research partners, native-speaking language partners, etc.)
• Have students connect select reading(s) to course experiences (e.g., labs, field experiences, class discussions). 
• Leverage Canvas-based tools that promote student-to-student interactions (e.g., Hypothesis for social annotation or FeedbackFruits for peer review and feedback).
• Have students provide a reflective rationale for choices made throughout the completion of a class project (e.g., an artist statement, response to a reflection prompt about personal relevance of source selections)
• Have students connect course experiences/motivations to their own lived experiences.

Create Transparent Assignment Materials

Once you have thought about whether or not generative AI can be effectively incorporated into your assignments, it is important to create assignment materials that are transparent (Winkelmes, et al., 2019). Specifically, this means creating ways to communicate to students the task you are are requiring, along with its purpose and evaluative criteria:

• Task. Students will benefit from having a clear and accessible set of directions for the project or assignment you are asking them to complete. 
• Purpose. Students are often more motivated when they understand why a particular task is worth doing and what specific knowledge or skills they will develop by completing the assigned task.
• Evaluative Criteria. Students benefit from having a clear sense of how their work will be evaluated and a full understanding of what good work looks like.

Communicate Your Expectations for Generative AI Use 

Regardless of the extent to which you incorporate the use of generative AI into your assignment design, it is essential to communicate your expectations to students. Sharing clear directions for assignments, communicating how students can be successful in your class, and promoting academic integrity serves both you and your students well. 

Example Assignment Policy Language for Generative AI Use

The following language on the use of generative AI may be helpful as you create directions for specific assignments. Please note that the following sample language does not reflect general, course-level perspectives on the use of generative AI tools. For sample course-level statements, see AI & Academic Integrity .

Prohibiting AI Use for a Specific Assignment

Allowing the use of generative ai for a specific assignment with attribution.

For full details on how to properly cite AI-generated work, please see the APA Style article, How to Cite ChatGPT . "

Encouraging the Use of Generative AI for a Specific Assignment with Attribution

For full details on how to properly cite AI- generated work, please see the APA Style article, How to Cite ChatGPT ."

Confer with Colleagues

There is almost always a benefit to discussing an assessment plan with colleagues, either within or beyond your department. Remember, too, that CTI offers consultations on any topic related to teaching and learning, and we are delighted to collaboratively review your course assessment plan. Visit our Consultations page to learn more, or contact us to set up a consultation.

2023 EducaUse Horizon Report | Teaching and Learning Edition. (2023, May 8). EDUCAUSE Library. https://library.educause.edu/resources/2023/5/2023-educause-horizon-report-teaching-and-learning-edition

Antoniak, M. (2023, June 22). Using large language models with care - AI2 blog. Medium. https://blog.allenai.org/using-large-language-models-with-care-eeb17b0aed27

Dinnar, S. M., Dede, C., Johnson, E., Straub, C. and Korjus, K. (2021), Artificial Intelligence and Technology in Teaching Negotiation. Negotiation Journal, 37: 65-82. https://doi.org/10.1111/nejo.12351

Jensen, T., Dede, C., Tsiwah, F., & Thompson, K. (2023, July 27). Who Does the Thinking: The Role of Generative AI in Higher Education. YouTube. International Association of Universities. Retrieved July 27, 2023.

OpenAI. (2023, February 16.). How should AI systems behave, and who should decide? https://openai.com/blog/how-should-ai-systems-behave

Winkelmes, M. A., Boye, A., & Tapp, S. (2019). Transparent design in higher education 

teaching and leadership: A guide to implementing the transparency framework institution-wide to improve learning and retention. Sterling, VA: Stylus Publishing .

Teaching Commons Conference 2024

Join us for the Teaching Commons Conference 2024 –  Cultivating Connection. Friday, May 10.

Integrating AI into assignments

Main navigation.

Here we offer strategies and perspectives on integrating AI tools into assignments and activities used to assess student learning.

Creating your course policy on AI

• An effective syllabus works to motivate learning, define goals, explain course structure, and provide support to students as they learn.
• Be clearly stated and specific
• Clarify the context or conditions of allowable AI use
• Explain processes and consequences for non-compliance
• Have a thoughtful pedagogic rationale in support of student learning
• Connect to support resources
• Show support for student well-being

Outcomes for this module

In this module, we will analyze activities and assignments used for assessing learning, provide student-centered perspectives, and offer strategies for developing assessment activities and assignments that integrate student use of generative AI chatbots.

After completing this module, you should be able to:

• Describe why your assessment activities are meaningful to learners.
• Identify and clarify the learning objectives of your assessment activities.
• Identify relevant strategies that can be applied to assessment activities in your course.
• Empathize with student perspectives on using AI in course assessment activities.

Warm-up with a metacognitive exercise

As you begin to explore, think about what you already know and the opinions you may already hold about the educational aspects of AI chatbots. This metacognitive exercise can help you identify what you want to explore and what you already understand. Making connections to what you already know can deepen your learning and support your engagement with these modules.

Begin with the prompt, “Describe an assignment or assessment activity that integrated technology in a way that was effective and engaging for your learning,” and respond to the poll below.

Unpacking your assessment activities and assignments

When designing or adapting an activity or assignment used to assess learning, whether you integrate AI or not, we encourage you to consider two questions: why is this meaningful, and what are students supposed to learn from it?

Define why it is meaningful

Students can learn better when they are motivated and can make meaningful connections to coursework (Headden & McKay, 2015). We might assume that students’ motivations focus on their grades, but that assumption does not provide the full picture, and when applied in isolation it is not likely to sustain deep learning. Articulating what makes an activity meaningful, motivational, and memorable for students can help you create an engaging activity or assignment that enhances student learning and motivation.

Concerning AI chatbots, perhaps the activity or assignment addresses AI in ways that prepare students for future careers, enhance their social connections, or touch upon broader issues they care about. We encourage you to talk with your students about what they find meaningful to inform the design of your activities and assignments. What leads them to want to engage?

Also, reflect on why the assignment is meaningful to you. Is it simply convenient to implement (and standard in your experience as a student and teacher) or does it connect to something deeper in your pedagogy? Perhaps the assignment reinforces the norms and values that you share with other professionals in your discipline, allows you to connect with students in more meaningful ways, builds foundational skills for other parts of the curricula, or explores emergent opportunities and challenges with AI for your field.

Define what students are intended to learn

Next, identify and clarify the underlying learning objectives of the assignment or activity. The objective should describe the observable skills or behaviors students will have learned to perform after completing the activity. Clearly articulated learning objectives can help you develop activities that support learning and assessments that accurately measure student learning.

When thinking about AI chatbots and how they impact writing, you might ask yourself, “What are the underlying learning objectives being addressed through writing?” Instructors may assign writing tasks to assess how students engage with content. In the past, teachers could assume with good reason that a student producing coherent writing must have engaged with the content to generate writing that makes sense. However, we might also question this assumption about the automatic connection between coherent writing and deep engagement. The advent of generative AI has certainly exacerbated this.

Do you ask your students to write to demonstrate and reinforce content knowledge? Do they write to analyze and critique a position? Do they write to formulate arguments and cite evidence? Do they write as a form of creative expression? When you think about the available options, you can likely develop many ways for students to learn and demonstrate these skills with or without writing. Ultimately, honing in on the underlying learning objectives can help you integrate generative AI tools into an assignment.

Students can benefit from understanding how AI works and the educational opportunities and challenges that it presents. Consider offering the content in the modules in this guide to your students as supplemental reading or as part of a class activity.

Strategies for implementing AI into activities and assignments

As you think through how you might address or integrate AI tools in an assessment activity or assignment, we encourage you to consider a range of possibilities related to the specific aims of your course and the needs of your students. Here we offer a variety of pedagogical strategies for you to consider. We present these strategies in the context of students using AI chatbots, but they also apply to contexts without AI. Remember why your assignment is meaningful in relation to your learning objectives to help you select appropriate strategies.

Leverage multiple modalities

Consider ways to diversify when and where you assess student learning and the formats students use to express what they’ve learned.

Use more in-class assignments

Strategies like the flipped classroom model assign lecture content as homework and use the in-class time for learning activities (Lage et al., 2000). You can use this in-class time to integrate more low-stakes assessment activities during which you can better guide students toward using AI in ways that support learning.

Multiple modes of expression

Students may differ in how they can best articulate what they know. Using multiple modalities of expression, such as having students complete assignments that require speaking or graphic representations instead of only written text, stands out as an established strategy within the Universal Design for Learning framework that could apply here. While chatbots primarily generate written text, other AI tools can generate music, graphics, and video. You can thus create assessment activities that integrate multiple modalities at once.

For example, if you are assessing students’ understanding of cultural exchange in the ancient world, students might create a mind map or timeline to visually represent important trends, events, or concepts covered in the assigned readings. AI might then be used to generate images of artifacts, portraits, or cityscapes based on historical descriptions.

Make grading practices clear

Consider ways to clarify for students how they are being graded and what is expected of them.

Require robust citation

Have students learn about and adopt more robust citation practices, especially if they use AI tools for writing. You might begin with conversations about what plagiarism entails and why ethics matter in higher education and your discipline. Then connect students to resources on citation and documentation .

If you and your students decide to use AI tools, you can find style guidelines about citing AI-generated text for APA style and MLA style . These guidelines advise writers to cite the AI tool whenever they paraphrase, quote, or incorporate AI-generated content, acknowledge how they used the tool (for brainstorming, editing, and so on), and vet secondary sources generated by AI. For example, students could include citations for AI in the Works Cited section of their work and also include a statement describing why and how they used AI chatbots.

Establish and communicate clear assessment criteria

Try to bring assessment activities, learning objectives, and evaluation criteria into alignment. For example, if your objectives and assessments center around students proposing a solution to an open-ended problem, then the evaluation criteria might touch upon the feasibility, impact, or comprehensiveness of the proposed solutions. The criteria can vary a lot depending on your content and course, but your students benefit when you communicate these criteria and the purpose and reasoning behind them (Allen & Tanner, 2006).

For example, when integrating AI chatbots into a writing task for students, you might put more weight on the quality of their ideas and the validity of cited sources and less weight on structure, grammar, and word choice. You might then create a rubric that you discuss with students in advance so they have a clear understanding of what will guide you in assessing their work.

Assess learning throughout the course

Consider ways to assess student learning throughout your course as opposed to assessing mostly at the end of the course.

Emphasize the process

You may be able to more effectively assess student learning during the different stages of the process as opposed to assessing learning based on their finished work (Xu, Shen, Islam, et al., 2023). Whether or not students use AI tools, they can benefit from segmenting a large project into smaller components with multiple opportunities for feedback and revision. Also, consider how you might adjust grading criteria or grade weights to put more emphasis on the process.

For some steps in the thinking process, such as brainstorming ideas, formulating a position, and outlining a solution, allowing students to use AI tools might benefit their process. For example, you might have students begin with low-stakes free-writing, such as brainstorming, then use AI chatbots to explore possible areas for further investigation based on the ideas students generate through their exploratory writing. Students might then critique and revise the AI-generated ideas into an outline.

Leverage formative feedback

Teachers provide formative feedback to students throughout the learning process to stimulate growth and improvement. Formative feedback can help students identify misunderstandings, reinforce desirable practices, and sustain motivation (Wylie et al., 2012). You and the teaching team might provide feedback directly to students or you might facilitate students giving feedback to each other. You might then assess how students follow up on feedback they receive.

You can use AI tools to inform your feedback to students or generate feedback directly for students. AI tools could provide instant, individualized feedback efficiently and frequently, supplementing the feedback provided by your teaching team. For example, you might share your existing assignment, rubric, and sample feedback with the chatbot and give it instructions on when and how to give feedback. Importantly, you should review feedback generated by chatbots for accuracy and relevance. Refine and save the prompts that work best. You might later share the prompts you’ve developed with students so they may use them to generate feedback themselves.

Make assignments more meaningful

Consider how you might make your assignments more relatable and meaningful to your students.

Personalize assessments

When done thoughtfully, connecting assessments to the personal experiences, identities, and concerns of students and their communities can help to motivate and deepen learning (France, 2022). You might also connect assignments to contexts specific to Stanford, your course, or your specific group of students.

With AI, you or your students might generate practice questions on topics that came up during a specific class discussion or generate analogies for complex concepts based on their interests and backgrounds. You might ground an assessment activity in local contexts, such as having your engineering students propose a plan to improve Lake Lagunita.

Use real-world assessment tasks

Assignments that leverage real-world problems, stakeholders, and communities that students are likely to engage with in their work lives can be motivational and valid ways of evaluating a student’s skills and knowledge (Sambell et al., 2019).

For example, students might work with real (or AI-simulated) business or community partners to develop a prototype product or policy brief. Students might have more time to work with those stakeholders and refine their proposal concepts if they can use AI tools to assist with time-consuming tasks, such as summarizing interview transcripts, writing a project pitch statement, or generating concept images.

AI itself might provide a relevant topic of study for your course. For example, you might examine AI as part of a discussion in a course about copyright and intellectual property law. Or you might analyze AI companies such OpenAI or Anthropic as case studies in a business course.

Assess more advanced learning

Consider ways you might assess more advanced or wider-ranging learning goals and objectives.

Emphasize metacognitive reflection

Metacognitive reflection activities, where students think about what and how they learn, can help students improve their learning (Velzen, 2017). You might use polls, discussion activities, or short writing exercises through which students identify what they already know about the topic, what they learned, what questions remain, and what learning strategies they might use for studying.

AI chatbots can help guide the reflection process like this reflection tool being developed by Leticia Britos Cavagnaro at Stanford d.school . Or perhaps students complete some activities with AI, then reflect on how it benefits or hinders their learning, and what strategies they might use to best leverage AI for learning.

Prioritize higher-order thinking

While students should develop mastery over foundational skills such as understanding concepts, identifying key characteristics, and recalling important information, practicing higher-order thinking skills, such as solving complex problems, creating original works, or planning a project, can deepen learning. For example, you might frame student essays as a defense of their views rather than a simple presentation of content knowledge. You might adjust assessment criteria to prioritize creativity or applying skills to new contexts.

Prioritizing higher-order thinking can encourage students to use AI tools to go beyond simply generating answers to engaging deeply with AI chatbots to generate sophisticated responses. Students could conduct preliminary research to find reliable sources that verify or refute the claims made by the AI chatbots. AI chatbots might then generate feedback, provide prompts for further reflection, or simulate new contexts.

Putting it all together

Here we offer a practical example: first, a typical assignment as usually designed, and then how you could enhance the assignment with some strategies that integrate AI chatbots.

When thinking about your course, start with small changes to one assignment and steadily expand upon them. Try to use AI chatbots for your other work tasks to build your fluency. Talk with students and colleagues about how the changes to your course work out concerning student engagement and learning. When integrating AI into an existing assignment, begin with an assignment that already has clearly defined learning objectives and rationale. Begin by using AI or other technology to supplement existing parts of the process of completing the assignment.

More examples of AI assignments

• AI Pedagogy Project from metaLAB (at) Harvard
• Exploring AI Pedagogy from the MLA-CCCC Joint Task Force on Writing and AI
• TextGenEd: Continuing Experiments, January 2024 Collection from WAC Clearinghouse

Example of an assignment without AI

Currently, your students in an epidemiology course write essays summarizing the key concepts of an academic article about the socio-determinants of diabetes . This assessment activity has meaning because it focuses on a foundational concept students need to understand for later public health and epidemiology courses. The learning objective asks students to describe why socio-economic status is a strong predictor for certain diseases. Students write a five-page essay about a disease that can be predicted by socio-economic status including at least three additional citations. Students complete the essay, which counts for 30% of the final grade, before the final exam.

An example of an assignment that integrates AI

Using some of the strategies in the above sections, you might redesign this assignment to integrate the use of AI chatbots. Keep in mind that you would likely make small changes to a major assignment over multiple quarters. Consider some of the ideas below.

A meaningful assignment

The redesigned assessment activity carries more meaning to students because they might have personal experience of some communities adversely affected by these kinds of diseases, and public health issues like this intersect with other social injustices that students have expressed concern about.

Learning objectives

The objectives of the assessment activity include that students will be able to:

• Describe how this disease affects particular communities or demographics
• Explain the difference between correlation and causality regarding socioeconomic status and the disease
• Propose a public health intervention that could help to address this issue

Assignment elements with AI

Students generate explanations of medical terminology in the selected articles to aid with reading comprehension. They generate several analogies for the core concept that apply to their own life experiences and communities. Students share these analogies in a Canvas forum graded for participation. Instructors provide general feedback in class.

Informed by the article, students then prompt a chatbot with biographical stories for two fictional characters from communities they care about incorporating differing socio-economic factors. Then they guide the chatbot in generating a dialogue or short story that illustrates how the two characters could have different health outcomes that might correlate with their socio-economic status. Students might use AI image generators for illustrations to accompany their stories. Students submit the work via Canvas for evaluation; the teacher shares exemplars in class.

Using an AI chatbot prompt provided by the instructor, students explore possible ideas for public health interventions. The provided prompt instructs the chatbot only to help students develop their ideas rather than suggesting solutions to them. With the aid of the chatbot, the students develop a public health intervention proposal.

Assignment elements without AI

Students discuss the differences between correlation and causation, critically analyze the generated characters and stories, and address any biases and stereotypes that surfaced during the activity. You facilitate the discussion with prompts and guidelines you developed with the aid of AI chatbots. Students write an in-class metacognitive reflection that you provide feedback on and grade for completion.

Students draw posters that summarize their proposed intervention. They critique and defend their proposals in a classroom poster session. Students complete a peer evaluation form for classmates. You evaluate the posters and their defenses with a grading rubric that you developed with the aid of an AI chatbot.

Students write an in-class reflection on their projects summarizing what they have learned over the length of the project, how the activities aided their learning, and so on. This is submitted to Canvas for grading and evaluation.

Student-centered perspective on using AI for learning

When thinking about integrating generative AI into a course assignment for students, we should consider some underlying attitudes that we, the authors, hold as educators, informed by our understanding of educational research on how people learn best. They also align with our values of inclusion, compassion, and student-centered teaching. When thinking through ways to integrate AI into a student assignment, keep the following perspectives in mind.

AI is new to students too

Like many of us, students likely have a wide range of responses to AI. Students may feel excited about how AI can enhance their learning and look for opportunities to engage with it in their classes. They may have questions about course policies related to AI use, concerns about how AI impacts their discipline or career goals, and so on. You can play a valuable role in modeling thoughtful use of AI tools and helping students navigate the complex landscape of AI.

Work with students, not against them

You and your students can work together to navigate these opportunities and challenges. Solicit their perspectives and thoughts about AI. Empower students to have agency over their learning and to think about AI and other technologies they use. Teaching and learning are interconnected and work best in partnership. Approach changes to your teaching and course to empower all students as literate, responsible, independent, and thoughtful technology users.

Look at AI and students in a positive light

Education as a discipline has repeatedly integrated new technologies that may have seemed disruptive at first. Educators and students typically grapple with new technology as they determine how to best leverage its advantages and mitigate its disadvantages. We encourage you to maintain a positive view of student intentions and the potential of AI tools to enhance learning. As we collectively discover and develop effective practices, we encourage you to maintain a positive and hopeful outlook. We should try to avoid assuming that most students would use generative AI in dishonest ways or as a shortcut to doing course assignments just because some students might behave this way.

Assess and reinforce your learning

We offer this activity for you to self-assess and reflect on what you learned in this module.

Stanford affiliates

• Go to the Stanford-only version of this activity
• Use your Stanford-provided Google account to respond.
• You have the option of receiving an email summary of your responses.
• After submitting your responses, you will have the option to view the anonymized responses of other Stanford community members by clicking Show previous responses .

Non-Stanford users

• Complete the activity embedded below.
• Your responses will only be seen by the creators of these modules.
• Course and Assignment (Re-)Design , University of Michigan, Information and Technology Services
• ChatGPT Assignments to Use in Your Classroom Today , University of Central Florida

Works Cited

Allen, D., and Tanner, K. (2006). Rubrics: Tools for Making Learning Goals and Evaluation Criteria Explicit for Both Teachers and Learners. CBE - Life Sciences Education. 5(3): 197-203.

Ashford-Rowe, K., Herrington, J., & Brown, C. (2014). Establishing the critical elements that determine authentic assessment. Assessment & Evaluation in Higher Education, 39. https://doi.org/10.1080/02602938.2013.819566&nbsp ;

Bijlsma-Rutte, A., Rutters, F., Elders, P. J. M., Bot, S. D. M., & Nijpels, G. (2018). Socio-economic status and HbA1c in type 2 diabetes: A systematic review and meta-analysis. Diabetes/Metabolism Research and Reviews, 34(6), e3008. https://doi.org/10.1002/dmrr.3008&nbsp ;

CAST. (n.d.). UDL: The UDL Guidelines. Retrieved January 22, 2024, from https://udlguidelines.cast.org/&nbsp ;

Exploring AI Pedagogy. (n.d.). A Community Collection of Teaching Reflections. Retrieved January 22, 2024, from https://exploringaipedagogy.hcommons.org/&nbsp ;

France, P. E. (2022). Reclaiming Personalized Learning: A Pedagogy for Restoring Equity and Humanity in Our Classrooms (2nd ed.). Corwin.

Headden, S., & McKay, S. (2015). Motivation Matters: How New Research Can Help Teachers Boost Student Engagement. Carnegie Foundation for the Advancement of Teaching. https://eric.ed.gov/?id=ED582567&nbsp ;

Hume Center for Writing and Speaking. (n.d.). Documentation and Citation. Retrieved January 22, 2024, from https://hume.stanford.edu/resources/student-resources/writing-resources… ;

Lage, M. J., Platt, G. J., & Treglia, M. T. (2000). Inverting the Classroom: A gateway to creating an inclusive learning environment. Journal of Economic Education, 31(1), 30-43.

metaLAB (at) Harvard. (n.d.). The AI Pedagogy Project. Retrieved January 22, 2024, from https://aipedagogy.org/&nbsp ;

MLA Style Center. (2023, March 17). How do I cite generative AI in MLA style? https://style.mla.org/citing-generative-ai/&nbsp ;

Office of Community Standards. (n.d.). What Is Plagiarism? Retrieved January 22, 2024, from https://communitystandards.stanford.edu/policies-guidance/bja-guidance-… ;

Sambell, K., Brown, S., & Race, P. (2019). Assessment to Support Student Learning: Eight Challenges for 21st Century Practice. All Ireland Journal of Higher Education, 11(2), Article 2. https://ojs.aishe.org/index.php/aishe-j/article/view/414&nbsp ;

The WAC Clearinghouse. (n.d.). January 2024. Retrieved January 22, 2024, from https://wac.colostate.edu/repository/collections/continuing-experiments… ;

U-M Generative AI. (n.d.). Course and Assignment (Re-)Design. Retrieved January 22, 2024, from https://genai.umich.edu/guidance/faculty/redesigning-assessments&nbsp ;

Van Velzen, J. (2017). Metacognitive Knowledge: Development, Application, and Improvement. Information Age Publishing. https://content.infoagepub.com/files/fm/p599a21e816eb6/9781641130240_FM… . ISBN 9781641130226. 

Wylie, E. C., Gullickson, A. R., Cummings, K. E., Egelson, P., Noakes, L. A., Norman, K. M., Veeder, S. A., ... Popham, W. J. (2012). Improving Formative Assessment Practice to Empower Student Learning. Corwin Press.

Xu, X., Shen, W., Islam, A. A., et al. (2023). A whole learning process-oriented formative assessment framework to cultivate complex skills. Humanities and Social Sciences Communications, 10, 653. https://doi.org/10.1057/s41599-023-02200-0  

Yee, K., Whittington, K., Doggette, E., & Uttich, L. (2023). ChatGPT Assignments to Use in Your Classroom Today. UCF Created OER Works, (8). Retrieved from https://stars.library.ucf.edu/oer/8  

You've completed all the modules

We hope that you found these modules useful and engaging, and are better able to address AI chatbots in your teaching practice. Please continue to engage by joining or starting dialogues about AI within your communities. You might also take advantage of our peers across campus who are developing resources on this topic.

• Institute for Human-Centered Artificial Intelligence
• Accelerator for Learning
• Office of Innovation and Technology , Graduate School of Education

We are continuing to develop more resources and learning experiences for the Teaching Commons on this and other topics. We'd love to get your feedback and are looking for collaborators. We invite you to join the Teaching Commons team .

Learning together with others can deepen the learning experience. We encourage you to organize your colleagues to complete these modules together or facilitate a workshop using our Do-it-yourself Workshop Kits on AI in education. Consider how you might adapt, remix, or enhance these resources for your needs. 

If you have any questions, contact us at [email protected] . This guide is licensed under  Creative Commons BY-NC-SA 4.0 (attribution, non-commercial, share-alike) and should be attributed to Stanford Teaching Commons.

Considerations for Using AI in the Classroom

Created by Laura Schmidli with Molly Harris, Alison Caffrey, Antonella Caloro, Jonathan Klein, Luis Loya, David Macasaet, Erika Schock, and Parker Story. Published January 5, 2023. Updated December 8, 2023.

In late 2022, ChatGPT made headlines. This and other generative artificial intelligence (GenAI) tools have many in higher education discussing AI’s potential threat to our work and purpose. To read more from late 2022 and early 2023, see References and Further Reading .

Like with any new technology, one approach instructors can take in the classroom is to transparently make use of it. This allows you to move beyond stress over whether or not students are using GenAI, and instead have a voice in when, why, and how you and your class use it. You can even invite students to consider and explore AI with you (Tufekci, 2022). Although this approach may not work or be right for all instructors and courses, this strategy has the advantages of encouraging student participation in a larger societal question and helping students to develop their own ethical grounding and practical understanding of academic integrity related to AI.

Check out our 2024 Article!

In Revise Assignments in Response to Generative AI , we consider generative AI and assignments, using research literature and instructor and student perspectives. How are student and instructor perspectives on generative AI shaping classroom activities and vice-versa? What adaptations to assignments have been successful for instructors and students in L&S? Read the new article to learn more and consider applications in your classroom.

Steps to Consider

This is an accordion element with a series of buttons that open and close related content panels.

1. Reflect on threats and opportunities.

People have raised concerns for student academic integrity as well as for the longer term impact on learner motivation, engagement, and knowledge retention. Others in your discipline may also have specific concerns related to knowledge production, values, and more. What resonates for you?

However, there are also potential benefits. GenAI may save time and effort on routine tasks, provide a new perspective on a problem, or generate content that can be analyzed or critiqued in the classroom.

How do you personally weigh the threats and opportunities in your classroom, and for your own work?

2. Consider what information is safe to share.

Before using any tool or technology, instructors and students should review its data retention and privacy policies – e.g., the OpenAI FAQ for ChatGPT. The general recommendation from campus IT is to only enter information into these tools that you are comfortable making public. See Generative AI @ UW-Madison: Use & Policies for more specific guidance.

In a classroom setting, instructors must also consider information you are asking students to share through use of any non-UW tool, including GenAI. Tools and technologies that are not supported by UW may present risks to instructors and students by not meeting requirements for privacy, security, intellectual property, and records retention. See Use of Third-Party Applications for specific considerations and limitations.

3. Choose one or more GenAI tools to try.

OpenAI’s ChatGPT has continued to be freely available, with a more robust version available for subscription purchase, but requires creating an account using an email address and phone number. Google Bard is also freely available, but does require a Google account.

In contrast, Bing Chat is available for free and does not require an account. Other tools that require less personal information are also available.

4. Investigate strengths and weaknesses of GenAI relative to your course and work.

If provided with a prompt or assessment question from your class, how does the GenAI tool perform? Experiment with questions, tasks, and assignments related to your work, study, or teaching. What are GenAI tools good at, and where do they it struggle? With which routine tasks are you comfortable asking for GenAI assistance?

Keep in mind that writing productive prompts for GenAI requires some skill and practice. See OpenAI’s guidance for designing prompts for ChatGPT.

5. Consider revisions to your assignments.

Making your questions more personal, reflective, specific, local, or complex (i.e., requiring higher order thinking) may make it more difficult for students to use AI to adequately complete them. But more importantly, these changes can make your questions more interesting and valuable to your students.

When designing an assignment where students can use a GenAI tool, always provide an alternative for students who don’t want to share their data with a third party tool (i.e., students shouldn’t have to share their data to be successful). Alternatives could include making part of the assignment optional, the instructor engaging with the AI on behalf of students, students using a different AI language model that does not require personal information, or students using another supplemental source (e.g., interview with a person, responses on social media, review article, etc.) in place of GenAI.

6. Identify and communicate opportunities in your course.

Many students are already using GenAI on their own, and this will likely increase as these tools are integrated into more technologies we use regularly. When instructors acknowledge and model GenAI use, we can guide students in considering the capabilities of these tools, surface differing opinions around fairness, help students align use of these tools with their own ethical frameworks, and even help students grapple with anxiety about the future.

Make your policy on GenAI use in your class overall and in specific assignments (if applicable) clear to students from the start of class. Review the ideas below for exploring AI with your students and consider where GenAI might intersect your course.

Share Your Ideas for Using AI

We’d love to add your knowledge to this guide. What plans, ideas, questions, or concerns do you have for using AI in your classroom?

Share Your Idea

Activity Ideas That Explore Capabilities and Limitations of AI

Ask 20 Questions of AI: In small groups, students collaborate to write 20 questions for a text-generating AI about how it works. In a larger group, they consider what the AI’s responses mean for academic integrity, authority, validity, trust, or other important ideas in your course. 

Analyze AI Perspectives: The instructor asks the text-generating AI to respond to a prompt as a specific person – e.g., a historical figure. Students then critique the AI’s response, drawing on their interpretation of the person’s perspective. 

Predict Where AI Excels: Individually students construct one question or prompt on a specific topic that they think text-generating AI can respond to successfully, and another prompt or question they think AI responds to unsuccessfully. In a larger group, students share their work to identify characteristics of prompts to which AI struggles to respond. For a related lesson outline, see Critical Analysis Across AI Tools & Stereoptypes from the AI Pedagogy Project at Harvard’s metaLAB.

Compare Exam Questions: Individually students write one multiple choice exam question and ask text-generating AI to write a second. In a larger group, students analyze which submitted questions are AI-written, which are human-written, and evaluate which provide a better assessment of learning.

Evaluate AI Output: The instructor uses AI to generate work, like a thesis, short analytical paper, theater dialogue, computer code, image, or even musical composition. In groups students analyze the sample work created by AI, with particular attention to evidence, sources, perceived bias, or other important elements for your course. Students can then revise it for improvement in groups, and share back revisions for comparison. For an example lesson outline, see Correct a Bad Essay from the AI Pedagogy Project at Harvard’s metaLAB.

Activity Ideas That Integrate AI into the Writing Process

Rubric Calibration with AI Writing: The instructor uses AI to generate an essay, thesis, or other written work. Groups then use a rubric to evaluate the AI’s work, and suggest changes or improvement to the rubric. This can help students think about how they define high-quality work, and how a rubric might help identify AI-generated work. 

Planning and Evaluating AI Use: Students create a plan for using AI within a specific assignment, like a scaffolded research paper, where they articulate for which steps it is valuable and appropriate to use AI, and when original thought and creativity are needed and why. This activity works best when sequenced with other activities that explore AI capabilities.

AI Drafting Process: Students use AI to generate a draft of a simple writing assignment. Students then analyze the AI’s writing, focusing on accuracy, bias, or other characteristics important in your course. You may also ask students to improve the AI’s draft to complete a second draft.

AI Feedback: Students ask AI to evaluate an initial draft of a short writing assignment, asking AI to focus on a specific element. Students then incorporate any valuable feedback into their work, and share their revisions with a small group. This can help students get another perspective on writing quickly, while encouraging them to consider that feedback critically.

AI Thesis Revision: Students use AI to quickly generate thesis statements on a variety of topics. Individually students revise these statements and share two that are strongest to a group for feedback, including what prompts they provided the AI and what revisions they made to each statement. Students use AI to “get started” by quickly generating ideas, and then leverage their own skills to refine and improve.

Writing with Images: Students or instructors use image-generating AI as part of a reflective writing, freewriting, or creative writing process in any language. Students can use AI to quickly visualize descriptions from their writing, or students or instructors can use AI to generate images that prompt elaboration in writing. For an example lesson outline for generating images, see AI Image Remixing from the AI Pedagogy Project at Harvard’s metaLAB.

Ways to Establish Norms and Boundaries for Using AI in Your Classroom

Co-create Class Expectations: Students collaborate to suggest “ground rules” for using AI within a specific course or assignment. As a class, consider specific tasks where AI is helpful, tasks where AI is unhelpful, when students and instructors think using AI is cheating, and if and how students should cite AI in their work. Ultimately the class will produce documented expectations with the instructor for using AI. For an example lesson outline related to co-creating and discussing expectations, see Debating the Ethics of Generative AI from the AI Pedagogy Project at Harvard’s metaLAB.

Structure an AI Discussion: Based on the “structured academic controversy” model, students are assigned a stance related to using AI in the classroom. Groups collaborate to develop arguments for one perspective and take turns presenting while the other team listens actively and then summarizes the arguments they heard. Individually or in a large group, students then reflect on what they learned, how their personal stance may differ from the stance they were assigned, and whether or not their personal position has changed.

Make Instructor Expectations Clear: Whatever your aims for using (or prohibiting) the use of AI within your classroom, make your expectations clear to students at the semester’s start. This may include adding a statement to your existing academic integrity statement, and reviewing expectations with students in class. Students should also have the option to not use any tool that requires personal information shared with a third party not contracted by the University.

Additional Resources

Connect with help.

We are happy to connect with instructors about using AI in your classroom, designing assignments, or brainstorming solutions for your course. Meetings typically last 45 minutes and take place virtually. We listen carefully to understand your needs and recommend actionable next steps.

Request a Meeting

Generative AI Research Guide

Created for a student audience by UW-Madison Science and Engineering Librarians, this Research Guide provides an overview of how these tools work and considerations when using them in course work, including tips for citing these tools.

• Generative AI , UW-Madison Libraries Research Guides

Example Assignments and Lesson Outlines

The metaLAB at Harvard is curating assignments that integrate AI tools, contributed by instructors from around the world.

• Assignments from the AI Pedagogy Project from metaLAB at Harvard

AI & Academic Misconduct

We recognize that the advancement of AI creates concern about academic integrity enforcement. While the focus of this guide is different, the following resources may be helpful for students and instructors.

• Generative Artificial Intelligence , Office of Student Conduct and Community Standards
• Academic Misconduct, Office of Student Conduct and Community Standards

Guidance for Writing

UW-Madison’s Writing Across the Curriculum staff have collaborated to draft guidance for instructors on supporting student writing practices in an age of AI, which will evolve as campus guidance and policy changes.

• AI-Generated Text: Considerations for Teaching and Learning Writing

References & Further Reading

• Barbaro, M., et al. (2022, December 16). Did Artificial Intelligence Just Get Too Smart? The New York Times . https://www.nytimes.com/2022/12/16/podcasts/the-daily/chatgpt-openai-artificial-intelligence.html
• ChatGPT. (2023). In Wikipedia . https://en.wikipedia.org/w/index.php?title=ChatGPT&oldid=1132927055
• Jolles, Ward. (2023, January 4). New AI technology writes essays for you—And UW-Madison students are using it . Retrieved January 5, 2023, from https://www.wkow.com/news/new-ai-technology-writes-essays-for-you-and-uw-madison-students-are-using-it/article_4b051b8a-8ca2-11ed-8d15-3b4d9fa4403b.html
• Marche, S. (2022, December 6). The College Essay Is Dead . The Atlantic. https://www.theatlantic.com/technology/archive/2022/12/chatgpt-ai-writing-college-student-essays/672371/
• Roose, K., Newton, C., Land, D., Szuchman, P., Powell, D., Ittoop, E., Niemisto, R., & Moxley, A. (2022, December 9). Can ChatGPT Make This Podcast? The New York Times . https://www.nytimes.com/2022/12/09/podcasts/can-chatgpt-make-this-podcast.html
• Thunström, A. O. (2022, June 10). We Asked GPT-3 to Write an Academic Paper about Itself;Then We Tried to Get It Published . Scientific American. https://www.scientificamerican.com/article/we-asked-gpt-3-to-write-an-academic-paper-about-itself-mdash-then-we-tried-to-get-it-published/
• Tufekci, Z. (2022, December 15). Opinion | What Would Plato Say About ChatGPT? The New York Times . https://www.nytimes.com/2022/12/15/opinion/chatgpt-education-ai-technology.html
• USING AI TO WRITE ESSAYS ISN’T CHEATING, STUDENT SAYS . (2022, May 16). Retrieved November 13, 2022, from https://www.canta.co.nz/canta/newsarticle/115524?newsfeedid=1453013
• Warner, J. (2022, December 11). ChatGPT Can’t Kill Anything Worth Preserving. The Biblioracle Recommends . Retrieved January 3, 2023, from https://biblioracle.substack.com/p/chatgpt-cant-kill-anything-worth
• Wolfram, S. (2023, January 9). Wolfram|Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT . Retrieved January 20, 2023, from https://writings.stephenwolfram.com/2023/01/wolframalpha-as-the-way-to-bring-computational-knowledge-superpowers-to-chatgpt/

Acknowledgements

Thank you to Dorothea Salo, Dave Bloom and other UW Libraries staff, several anonymous commenters, and IDC team members for crowdsourcing and discussing these ideas.

How to Credit this Guide

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License . This means that you are welcome to adopt and adapt content, but we ask that you provide attribution to the L&S Instructional Design Collaborative and do not use the material for commercial purposes.

Example attribution: From Using Artificial Intelligence in the Classroom  by the L&S Instructional Design Collaborative,  licensed under the BY-NC 4.0 license .

• Our Mission

A Stoplight Model for Guiding Student AI Usage

Giving students guidelines for AI use on assignments—via a green, yellow, or red light—provides clarity around this powerful technology.

Artificial intelligence (AI) has the potential to revolutionize the way we teach and learn. However, with great power comes great responsibility. It’s crucial for us as educators to establish clear guidelines for students on when and where AI can be used in the classroom. This ensures that the technology serves as an aid to learning, rather than a crutch or a tool of academic dishonesty.

As teachers returned to school with an eagerness to incorporate AI into their instruction, our coaching team began helping them to develop clear guidelines for students on when it’s appropriate to use AI and when it is not. We believe that every summative assignment should include AI guidelines as part of the instructions, guidelines, and rubrics that students are already given.

To make it easy and rememberable, we condensed these guidelines into three actionable options: red light, yellow light, green light . 

Red Light: AI Usage Is Not Permitted in This Activity

This option is straightforward and leaves no room for interpretation. It is particularly useful for assessments or activities where the primary goal is to evaluate individual student understanding and skills. By explicitly stating that AI collaboration is not allowed, educators can maintain the integrity of the assessment process.

For assignments that fall under the “red light” category, think of traditional quizzes, exams, or short-answer questions that are designed to assess individual knowledge and skills. These are activities where the primary goal is to evaluate each student’s understanding of the material. Is the activity designed to assess individual understanding? Is it a formative assessment where collaboration could skew the results?

It’s essential to explain the rationale behind this restriction. Students are more likely to comply with rules when they understand the reasoning behind them. In these cases, teachers can have conversations with students about the importance of individual assessment. They can explain how this type of evaluation helps identify areas where improvement is needed and why academic honesty is a skill that will serve them well throughout their educational journey and beyond. Providing context helps students see the bigger picture and appreciate the importance of adhering to guidelines.

Providing clarity is especially important when students are working independently from home. When students are not physically present in the classroom, it can be tempting for them to seek AI assistance when they shouldn’t. Thus, it becomes paramount for educators to set clear expectations about when AI collaboration is permitted and when it is not. Just as teachers have guidelines for plagiarism, citing sources, etc., so can they have guidelines around AI use.

While it’s true that some students may not always adhere to the guidelines when working from home, it’s crucial to recognize that teaching responsible AI usage is a valuable educational opportunity. Instead of simply restricting AI access, we should aim to empower students with the knowledge and understanding they need to make responsible choices.

Yellow Light: permission from teacher required before using AI

This option offers a balanced approach, allowing for the possibility of AI usage while maintaining a level of oversight. The “yellow light” option is particularly useful for long-term projects that require extensive research, group activities where individual contributions are part of a collective grade, or case studies that could benefit from multiple perspectives. 

Incorporating AI tools into the classroom, such as Magicschool.ai, Diffit, and Perplexity, can enhance the learning experience in these scenarios. These technologies offer valuable resources that, when used with guidance and permission, can amplify students’ abilities to explore, learn, and contribute collectively. It is in these nuanced situations that the “yellow light” approach shines, facilitating the responsible integration of AI into the learning process, promoting teamwork, and fostering a deeper understanding of the subject matter.

When students ask for permission to use AI, it opens the door for a meaningful dialogue. Teachers can ask students to articulate what they hope to achieve with the aid of AI and how it aligns with the objectives of the activity. This conversation also provides an opportunity to discuss the ethical considerations of using AI, such as the importance of citing sources when incorporating external content. By requiring permission, educators can ensure that students have a clear understanding of the activity’s objectives and how AI can appropriately aid in achieving them.

Green light: Students are encouraged to use AI software

This option is the most open, encouraging students to explore the capabilities of AI in their learning journey. Assignments that are ideal for the “green light” option include creative writing tasks where AI can serve as a brainstorming tool, research projects that involve gathering and analyzing large sets of data, or activities that encourage innovation, such as coding projects or design tasks. 

However, the openness of this option necessitates a robust framework for ethical usage and academic integrity. Before diving in, students are required to discuss their planned approach with the teacher. This ensures that the use of AI complements rather than replaces human effort. The conversation also serves as a checkpoint for discussing how to properly indicate AI collaboration in their work and reinforcing the importance of transparency and ethical conduct.

Managing the “green light” option when dealing with a large number of students will certainly require planning. One strategy that teachers can employ to effectively oversee this open approach is to establish online discussion forums or collaboration spaces where students can share their plans for integrating AI into their work. These platforms can provide students with a space to post their ideas, seek feedback from both peers and the teacher, and foster a sense of collaboration.

Conversations and Considerations

These guidelines serve as a framework for teachers when assigning work. They are communicated explicitly at the outset of any assignment or activity where AI collaboration could be a factor. The advance notice is crucial; students are more likely to adhere to rules when they are aware of them beforehand and understand the reasoning behind them.

The conversation between educator and student during the “permission phase” of the yellow and green light options is invaluable. It serves not just as a checkpoint but as a teachable moment, helping students learn the nuances of academic integrity and ethical technology usage.

A valuable strategy to manage a full roster of students is to schedule regular check-in sessions, either individually or in small groups. During these sessions, teachers can discuss each student’s AI usage plan, offer personalized guidance, and ensure that ethical standards are upheld. 

The integration of AI in education is not a matter of if but when. As educators, we have the responsibility to guide our students in navigating this new landscape ethically and effectively. By being clear about the guidelines for AI usage in classroom activities, we can foster an environment that encourages innovation while maintaining academic integrity.

Guidance for the Use of Generative AI

About this guide:

Students and instructors are embracing ChatGPT (GPT-4 as of March 2023) and similar artificial intelligence (AI) technologies across disciplines for different learning goals. There is no one-size-fits-all best practice for their use. This document is meant as a guideline for instructors on what to consider as these tools evolve. We will provide strategies for adopting AI technologies in a responsible, ethical manner, and innovating within each discipline, major, and course. Exploring and communicating about the opportunities and limitations to using these tools will allow instructors and students to critically think about how knowledge is created.

Acknowledgements: This guide was a collaborative development which included contributions from the Center for Education Innovation and Learning in the Sciences, the Bruin Learn Center for Excellence, UCLA’s Online Teaching and Learning, Excellence in Pedagogy and Innovation in the Classroom, the Center for the Advancement of Teaching along with input from members of the Academic Senate, the Center for Accessible Education, Advanced Research Computing (Privacy and Governance), and University Registrar. Special thanks to Ava Arndt, Jess Gregg, Ilana Intonato, and Rachel Kennison for leading the writing and editing process.

UCLA Virtual Town Hall: What is ChatGPT and How Does it Relate to UCLA’s Academic Mission held on March 3, 2023, featured the following UCLA faculty panel:

• Dr. Safiya Noble, Professor of Gender Studies and African American Studies; Interim Director, UCLA DataX Initiative
• Dr. Ramesh Srinivasan, Professor of Information Studies; Director, UC Digital Cultures Lab.
• Dr. John Villasenor, professor of Electrical Engineering, Public Policy, Law and Management; Faculty Co-Director, UCLA Institute for Technology, Law and Policy

What is ChatGPT?

ChatGPT is a “chatbot” developed by a private company called OpenAI. Users can enter question prompts and within seconds ChatGPT will produce text-based responses in the form of poems, essays, articles, letters and more. It can also create structured responses like tables, bulleted lists and quizzes. ChatGPT can provide translation and copy language style and structure. It can also be used to develop and debug programming code. New and expanded uses continue to be developed and launched. A similar tool called DALL-E uses AI to create art pieces, and other AI tools have been created or are in rapid development to do even more – music, animation, multimedia video, powerpoints – and the list goes on.

Are students using ChatGPT?

Yes, students have already been exploring and using it to support completion of their coursework. Some courses explicitly encourage the use of ChatGPT for assignments. However, one concern is that students may be using ChatGPT to draft responses to homework responses without learning the material, and this presents the challenges and opportunities for reflection on teaching and learning at this time.

Explore how ChatGPT works

CEILS Education Research Talk with Jess Gregg. Demo portion starts just after the 5 minute mark.

Revolutionizing Education with ChatGPT: How AI is Transforming the Way We Learn – Learning and Technology with Frank

Dig Deeper (article): How ChatGPT Works

Try out ChatGPT and Reflect: What are the opportunities?

Recommendation: Try out ChatGPT (or other AI tech) with your own course materials and assignments

Instructors can sign up for a free account at ChatGPT (or GPT-4) on Open AI’s platform . A first step in exploring the tool may be to enter some of your assignment prompts and assess the accuracy of the output. Then reflect on how you might embrace the tool or implement strategies that make use of the tool unnecessary.

PRO TIP: Including your students in the reflective process is also a learning opportunity to help them understand the benefits and limitations of the tool.

A few things to try:

• How would you evaluate the response provided by ChatGPT?
• Try modifying the prompt and see how that changes the response.
• Ask Chat GPT to synthesize text from large documents. For example, enter a 3500 word paper as a prompt, and ask ChatGPT to create an 18 slide PowerPoint presentation, with headings and bullet points, making a persuasive case for action.
• P rompt for writing samples specific to your area of expertise. For example, ask ChatGPT to generate a nurse practitioner note for a 53 year old male with hypertension presenting with shortness of breath and dizziness. Another example is to ask for an email introducing your upcoming course to enrolled students.
• Ask Chat GPT to translate something. Together with your students examine the translation to see how well it did. Ask for improvements, or consider when such translation capabilities might be
• If you teach students how to code , ask ChatGPT to correct incorrect code (debug code). Consider ways this might help students who are learning to code in your course.
• Reflect on the potential for ChatGPT to support student writing. Which writing skills do you feel are fundamental for students to do independent of artificial intelligence? How might ChatGPT facilitate the development of writing or problem solving skills?
• Have students use ChatGPT to write a draft and then have them edit what it produces or check for errors

Note: If you do not wish to create an account, reach out to your local teaching support to set up a consultation and explore your assignments together. There are also many demonstrations of ChatGPT available online that you can search and watch.

Ideas for Updating Your Course Activities with AI in Mind

Adjusting assignments and activities

• Ask students to use ChatGPT and “fact check” the response provided by finding primary and secondary sources to back up the information provided.
• Ask students to generate a first draft using ChatGPT then keep track changes in a document to refine/edit.
• Reflecting upon prompt engineering – -use prompting logic used by students to generate information and then provide a different prompt to help guide revision. Showcase that small changes can lead to major differences in output!
• The University of Wisconsin, Madison provides some examples for how to integrate AI into the writing process in your classroom

View this collaborative Google Doc: AI Examples and Resources to see examples and resources curated by UCLA’s teaching and learning community.

• Montclair State has created a guide that include “Practical Suggestions to Mitigate Non-Learning/Cheating”
• You can watch UCLA’s Will Conley, Department of Mathematics, provide a recorded overview of how to use Gradescope (approx. 56 mins). While we have now shifted to BruinLearn so the initial steps for linking to the gradebook will differ slightly, the within Gradescope interface is the same. At the 27 minute mark you can view what it looks like to see handwritten work submitted to Gradescope for streamlined digital grading by instructors and TAs.
• Require students make a connection to class discussions: Prompt students to explicitly reference in-class discussions, lecture material and course readings in their homework assignments. (Example: Share three takeaways from our in-class discussion on the issues with how Covid-19 testing was implemented across the US at the onset of the pandemic.)

Communicate: Talk With Your Students About AI

Discuss opportunities for AI to contribute positively to your discipline

Discuss the potential: Many of our students will go on to become leaders at organizations that utilize and/or develop new AI technologies. How will these tools support advancements in your field (medicine, science, art, music, humanities, health, and more)?

Prepare students for the future when they will work and interact with AI: This technology is likely to develop and become embedded in many parts of our lives. Preparing students to thoughtfully engage with it, co-create with it and be curious about and know how to interact with other technological developments as they occur.

Seize the opportunity to center the importance of critical thinking and digital literacy. Students will have the opportunity in the future to break the cycle of spreading disinformation, lack of journalistic integrity in news, and elevating accurate and factual research and scholarship. Emphasize the importance of digital literacy, research, and writing skills with students; connect students to library resources for research and writing. As educators, we have an obligation to help guide our students through many types of literacy, including digital media and AI literacy. UCLA’s WI+RE has created the Understanding Misinformation: A Lesson Plan Toolkit, that is geared towards educators who want to prepare students to learn about misinformation. We can get students to vet information like experts .

Lean in to talking to your students about how learning happens: Learning happens when actively engaging with the course material, through conversations and dialogue leading to deepening conceptual understanding.

Academic integrity: Provide clear expectations on how students should cite use of ChatGPT and AI in their work

Discuss Academic Integrity with Your Students:

One of the main concerns instructors have expressed is how to uphold academic integrity and prevent the misuse of tools like ChatGPT (intentional or not). These concerns include:

• Plagiarism (copying and pasting the response that the tool provides; running material through multiple AI generators to avoid detection)
• Lack of proper citation of sources
• Inaccurate, misleading, biased, false, or limited information in responses to question prompts. While some AI detectors have been recently developed, it is unclear how effective they will be long-term and early reports indicate that individuals can easily avoid detection through simple modifications to produced text.

The  UCLA Student Conduct Code  states, “Unless otherwise specified by the faculty member, all submissions, whether in draft or final form, to meet course requirements (including a paper, project, exam, computer program, oral presentation, or other work) must either be the Student’s own work, or must clearly acknowledge the source.” Unless an instructor indicates otherwise, the use of ChatGPT or other AI tools for course assignments is akin to receiving assistance from another person and raises the same concern that work is not the student’s own. Please communicate this to your students, and consider incorporating this language into your syllabus.

Teaching Assistants will be seeking guidance on how to discuss ChatGPT with students and what to do if they suspect submitted work may be AI generated. In addition to talking with your students, make space for conversations with your TAs and other instructional team members to explore this topic and co-construct guidelines.

The ultimate decision and responsibility for how to teach about AI and the establishment of or revision of course policies related to its use lies with the instructor.

View this collaborative Google Doc: AI Examples and Resources to see examples ( including Syllabus Language and Policy Language ) and resources curated by UCLA’s teaching and learning community.

Talk with your students about ethical issues and limitations related to AI development and use

Discuss the ethical issues and limitations  of AI

Facilitate discussions with your students on the impacts of spreading disinformation or biased information, lack of regulation of companies that develop these technologies, and other dangers. While students will likely still continue to use ChatGPT and other tools like it, it is crucial that our community has this shared understanding of both dangers and opportunities.

These technologies are not infallible and their accuracy is subject to a variety of factors, some listed below:

• Prone to filling in replies with incorrect data if there is not enough information available on a subject.
• Lack the ability to understand the context of a particular situation, which can result in inaccurate outputs.
• Large, uncurated datasets scraped from the internet are full of biased data that then informs the models.
• Data is collected from the past, it tends to have a regressive bias that fails to reflect the progress of social movements.

Our nation has yet to catch up to the regulation needed to prevent the potential for tremendous harm when false or biased information is taken as fact. Our community must continue to explore the value and innovation that can come from AI while simultaneously contributing to the dialog about these potential harms.

Share current examples of scholarly discussion on this topic.

As our own UCLA experts have shared with our instructional community during the recent UCLA Virtual Town Hall: What is ChatGPT and How Does it Relate to UCLA’s Academic Mission , there are concerns about the ethics and practices around tools like ChatGPT. Algorithms can and do replicate and produce biased, racist, sexist, etc. outputs, along with incorrect and/or misleading information.

Additional Examples:

• Educause – Special Report on Artificial Intelligence
• Noam Chomsky: The False Implications of ChatGPT
• Schools Must Embrace the Looming Disruption of ChatGPT

Be proactive in discussing concerns around privacy and intellectual property that students may have

On Requiring the Use of ChatGPT: Creating an account to use ChatGPT requires sharing of personal information. Depending on context, the use of ChatGPT may also mean sharing student intellectual property or student education records with ChatGPT under their terms and conditions of use. Individual students may have legitimate concerns and therefore may be unwilling to create an account. Discuss these concerns and consider alternatives.

• If you will be requiring use of ChatGPT, consider making this explicit in the syllabus (for a related example of considerations related to privacy, see Privacy Tips for Your Syllabus ).

Protecting student privacy as required by FERPA : Academic records, such as examinations and course assignments, are considered a student record and protected by FERPA. For example, ChatGPT should not be used to draft initial feedback on a student’s submitted essay that included their identifying information. Asking ChatGPT to respond to question prompts would not be a FERPA violation, as no student information is provided to ChatGPT.

ChatGPT is currently in the process of review through UCLA’s Third Party Risk Management to understand where there will be gaps in accessibility and security.

Ensure equity and accessibility concerns are addressed

As with any emerging technology, ChatGPT may not always be accessible by individuals with disabilities. Open a conversation with the Center for Accessible Education (CAE) for ideas on exploring accessible alternatives. As always, we encourage faculty to use this sample syllabus language to direct a student toward CAE to discuss their options for accommodations and support. Requests for support should be directed to [email protected] or the student’s listed Disability Specialist on their accommodation letter.

As the technology evolves, there may be a cost to using it, so continuing to revisit your learning goals and activities with respect to access is a critical equity issue.

Examples and Resources

Featured ucla resources.

WEBSITE: UCLA Online Teaching and Learning – Information on Chat GPT and AI – Resources from UCLA Online Teaching and Learning

CURATED RESOURCE LIST: Generative AI Tools and Resources – From Dr. Kim DeBacco, Senior Instructional Designer UCLA Online Teaching and Learning

SUBSTACK POST: “Carving out time to learn: A conversation with ChatGPT” – From Caroline Kong, Instructional Designer and Technologist at the Center for the Advancement of Teaching

RECORDED WEBINAR: “What’s All the Buzz About ChatGPT and AI in Higher Ed?”

RECORDED WEBINAR: UCLA Virtual Town Hall: What is ChatGPT and How Does it Relate to UCLA’s Academic Mission

RECORDINGS AND RESOURCES: AI in Action – Events brought to you by UCLA’s Center for the Advancement of Teaching (CAT), the Center for Education, Innovation, and Learning in the Sciences (CEILS), the Excellence in Pedagogy and Innovative Classrooms program (EPIC), Online Teaching and Learning (OTL), the Bruin Learn Center of Excellence (CoE), the Writing Programs, and Humanities Technology (HumTech)

UCLA NEWSROOM ARTICLE: “Can AI and creativity coexist?” – In a joint interview, UCLA professors Jacob Foster and Danny Snelson discuss how chatbots could be used in teaching, offer historic analogs for the current AI explosion and opine about whether technology is actually capable of creativity.

Example Syllabi Language and Activity Ideas

View this collaborative Google Doc: AI Examples and Resources to see examples and resources curated by UCLA’s teaching and learning community. This includes syllabus language, assignment ideas, and other strategies shared by instructors from UCLA and across the US.

70 Powell Library Box 951515 Los Angeles, CA 90095-1515

Subscribe to our Newsletter

Generative AI in your assignments

Can i use generative ai tools in my assignments.

Some subject coordinators may explicitly include information in your assessment guidance as to whether these kinds of tools may be used and how.  You must comply with the requirements of the assessment task – if you are unsure, check with your lecturer.

Tools such as AI chatbots can be helpful to explain concepts in different ways – this may help you to understand difficult concepts in your course.  Tools like ChatGPT can also potentially help you to think about an initial structure for an assignment: for example you might ask for section headings for a document based on your own notes, as a way to get started. 

In some cases, your lecturer may ask you to use ChatGPT or other generative AI tools as part of the assessment.  If this is the case, make sure that you understand how you are expected to use the tool and which parts of the work are expected to be your own original work.  If you are unsure, ask you tutor or lecturer for clarification. 

It is important to remember that when you submit an assignment or other assessment, you are taking responsibility for the content, and claiming it as your own work.  Whilst generative AI tools can be useful for helping you to understand a topic or structure your thinking, using them to write substantial parts of your work for you (where this is not explicitly required as part of the assessment) is academic misconduct and may have serious consequences for you.

• << Previous: Generative AI as a study tool
• Next: Generative AI in your research >>

AI-Resistant Assignments

Last Updated: Winter/Spring 2023

• Assignments that emphasize the writing process, rather than just the final product, will discourage students from using AI tools to do their work for them.
• Process-oriented assignments also tend to be more engaging and impactful for students.
• Framing your writing assignments as extensions of the class discourse challenges students to respond to the course content with new ideas of their own (something AI generally can’t accomplish).
• Making revision integral to the assignment helps students critically examine and improve their writing process, while making it harder to take AI-assisted shortcuts.
• Reflective and metacognitive writing assignments make students’ learning visible to them and to you; it also holds students accountable for the intellectual work of your course.

See assignment prompts that incorporate one or more of these principles.

At the time of this writing (winter 2023), the AI writing tool ChatGPT has recently launched, with several competitors soon to follow, and it’s clear that artificial intelligence will have a massive impact on the way we write, both inside and outside academia, for the foreseeable future.  As AI continues to evolve, so will our teaching practices, but one immediate concern for many instructors is the possibility that students may use ChatGPT and similar text-generation tools to avoid the intellectual work prescribed by many of our writing assignments.  

While the current generation of AI tools can’t produce particularly insightful or effective academic writing, that doesn’t mean students won’t try to substitute AI-written work for their own.  Furthermore, savvy users have already found more subtle ways to use ChatGPT to make their work as writers easier, such as using it to produce revisable first drafts or to shortcut the research process by identifying and summarizing a variety of sources on a given topic.  Whether these practices constitute academic misconduct or not is largely up to individual instructors to decide, but if you would personally consider them inappropriate for your courses, it’s worth considering how you might design new writing assignments or reconfigure old ones to make them less susceptible to digital assistance.

Fortunately, many of the existing best practices for designing writing assignments can also make them more difficult to complete with AI tools.  More importantly, though, they can also discourage students from turning to AI in the first place by placing greater value on the writing process, rather than just its product.  This helps to make the learning process more transparent and makes assignments more engaging, accessible, and impactful for students who complete them faithfully.

Making Writing an Extension of the Class Discourse

The best writing assignments will often ask students to engage not just the subject matter or source material of the course, but the discourse around that material that develops within the class itself.  A prompt, for example, might explicitly require students to respond to ideas that have come up in class discussion, or to apply concepts or themes that you’ve examined in class to a new text or subject.  However you frame it, the key to this approach is asking students to contribute something new to the discussion that explicitly builds on ideas they’ve encountered in your course.  In other words, ask students to make their writing an extension of the class itself, rather than an exercise that just happens to address the same basic material. This distinction can be subtle, but here are a few sample prompts that use this approach effectively .

This might not seem like a revelatory practice–after all, don’t all essay assignments require students to engage core ideas from the course?  But there’s an essential difference between simply engaging ideas from a course and responding to them effectively in conversation.  Engagement simply requires a student to understand the material and react to it.  Responding requires them to have a working understanding of the discourse around the material — who has said what, where previous speakers have agreed, disagreed, complemented and contradicted each other, and, most crucially, what remains to be said.  

As scholars, we all understand this implicitly; we review and cite other scholars because we want readers to see exactly where and how we’ve built upon the ideas that have come before, and we craft our arguments in ways that actively invite future scholars to respond to them.  Students, however, especially students who are new to college-level writing, tend not to think of their writing this way until they’re explicitly taught to do so.  High school classes and high-stakes standardized exams generally train students to see writing as a series of hurdles which they must complete for the sole purpose of demonstrating that they know the course material and can explain it in their own words.  Consequently, students often approach their writing exactly the way an AI would: by seeking to remix other people’s ideas in a way that fulfills the prompt, whether or not they say anything particularly new or interesting along the way.

Framing assignments as a way to build on the class discourse requires students to take a more active role through their writing, and in the course itself.  Once they come to understand that their writing will be an extension of the conversation taking place in the classroom, they start to realize that the more they participate in (or at least actively pay attention to) that conversation, the easier it becomes to engage it in writing.  They also become more invested in their writing, as they start to see the essay as a distillation of ideas that grew out of real interactions with real people, not a detached set of musings composed in isolation and shouted into the void (or the cloud).  

The writing produced this way is often messy, over-energetic, unfocused, underdeveloped, or otherwise heavily in need of revision. But it also tends to have a life and a voice that’s distinctive to the course, the term, the class, and the student all at once, and AI tools cannot match this distinctiveness. An AI can learn in the sense that it can gradually produce more refined output, but it can’t understand the ideas it synthesizes well enough to add anything distinctive and relevant to them. It can’t think , and that’s exactly what a good writing assignment will require students to do, above all else. Thus, any assignment that requires students to think — and to articulate their thinking clearly — in response to the ideas they encounter will resist AI’s intervention.

Creating Space for Revision

Most instructors encourage their students to make at least some effort to revise their writing.  We may implore them to start early, to consult the writing center, to read their essays out loud or to a friend, to form peer review groups, and so on. But it’s another thing entirely to make revision an integral and visible part of an assignment. Doing this not only places direct value on revision, but it also allows students to see and understand how revision works and why it’s so crucial to good writing and good thinking.

It’s important at this point to articulate a distinction that might seem obvious to any experienced writer, but is often revelatory to students: revision is not the same as editing. Editing (in this context, anyway) means examining and improving the presentation of one’s ideas–the grammar, the phrasing, the formatting, etc. Revision, on the other hand, means examining and improving the ideas themselves–fundamentally re-envisioning one’s conclusions and the tapestry of sources, responses, counter-responses, and epiphanies that lead to them. Most students don’t fully understand this distinction or, if they do, are not sure how to apply it to their own writing. They need to be taught how to revise, and this makes it hugely beneficial to them when revision becomes an integral part of an essay assignment.  When an instructor and a well-crafted assignment guide them through the revision process, many students discover for the first time what they’re really capable of as writers.

Granted, extended revision can be difficult to integrate into classes that are not explicitly designed to teach writing. Many instructors simply don’t have the luxury of time necessary to collect full drafts, comment on them in any significant way, and repeat again with the final drafts.  Fortunately, this is not the only way to create space for revision. Consider these alternatives, none of which are mutually exclusive:

• Simply spend some time in class discussing revision, giving students examples of what you would consider a solid first draft and solid final draft and offering various techniques for getting from the former to the latter (there are many, many resources for revision advice to be found online–find one that feels like the best fit for your assignment and point students there, or ask the WAC Director for suggestions).  Have students submit their rough drafts along with the final versions, and be sure to comment on how well the final draft improves on the earlier version in your feedback to the students.
• Conduct a peer review session, either in class or asynchronously through the cloud, in which students comment on each other’s drafts.  When they submit their final drafts, ask students to address if and how they responded to their peers’ comments.
• Set aside all or part of a class session on the day drafts are due, and have students evaluate their own drafts: what turned out well, what aspects are still in process, and how will they proceed with that knowledge? Have them turn this into a written revision plan, to guide the process to the final draft.
• In a class with multiple essay assignments, require students to choose one essay to revise and resubmit at the end of the term.  You can allow the revised essay to replace the grade of the earlier version, or make it a separate assignment grade (both approaches have their own pedagogical merits).

Each of these techniques helps to make revision an integral part of the assignment, not a side practice that we might encourage, but not explicitly require. They also create opportunities for you as an instructor to step in and guide students’ revision processes, helping them to see methods and opportunities to improve their writing that they don’t.  While this kind of feedback does require some time and attention on the instructor’s part, it can often allow for less feedback (and easier grading) on the final version of the assignment, as you’ll already have created a dialogue with the students around the assignment that you can simply bring to a close with a few explanatory notes and (ideally) a completed rubric.

The concrete ways that revision complicates the use of AI writing tools are fairly obvious. Essays produced by ChatGPT tend to be remarkably free from grammatical errors, but fairly vacuous; thus, they require little editing but a great deal of revision. And, since it’s generally harder to revise someone else’s work effectively than your own, students who produce their drafts with ChatGPT will often find that the revision process requires more work for less return.

Again, though, the real value of guided revision is that it encourages students to see their writing as a work in progress and to get a better sense of what they can accomplish with a fully developed writing process. The more pride and value they associate with their own writing, the less likely they’ll be to let AI do it for them.

Encouraging Reflection and Metacognition

The WAC Program has (to understate it mildly) promoted reflective and metacognitive writing as a teaching practice for some time, so it’s probably no surprise to see a section on them here. In the context of creating AI-resistant writing assignments, though, reflective and metacognitive writing take on additional layers of value, both because they help students to see the benefits of their own intellectual work and because they make it more difficult to conceal if they’ve allowed AI to do that work for them. 

Quickly stated, the distinction between the two modes is that reflective writing looks backwards (what have I learned and experienced?), while metacognitive writing looks forwards (how can these experiences inform my future actions and methods?).  These modes of thinking go together more often than not, and both are obviously essential for learning.  By challenging students to enact these processes–to actively consider, in writing, what they’ve learned and what they plan to do with that learning–we help them to connect the disparate pieces of their education, understand their own strengths and weaknesses more effectively, and simply develop a better understanding of themselves.

In practice, this is often a much simpler and smaller-scale operation than those principles would suggest.  Any formal writing assignment can be scaffolded fairly easily with one or more informal reflective and/or metacognitive tasks.  These tasks can (and generally should) be short and fairly simple both to write and to read.  They can happen at any point in the writing process–before, after, or even while the student is writing the assignment itself.  Consider a few common scaffolding assignments in this vein:

• A week or more before a formal writing assignment is due, ask students to write a paragraph or two summarizing their topic and articulating why they chose it (ideally, in the context of the ideas above, explaining how their assignment will respond to ideas that they have encountered in class).  Then, ask them to assess the work they’ll need to do to complete the assignment–what sources will they engage and how, what questions will they have to address, what conclusions do they still need to form, etc.?
• The weekend before the assignment is due, ask students to write a concrete plan for their entire writing process. How long do they think it will take to create an outline, write a draft, revise it, and proofread it? When and where will they do this work? What additional help, if any, will they seek out, from whom, and when?
• As they turn in the assignment, have students compose a short note to you about their writing process and how it worked out for them. How did their ideas change between conception and completion? What steps were easy or difficult? Did any of that surprise them? Overall, how happy are they with the final product as they submit it to you? Comment on this note as part of your feedback to the student — based on the final product, what aspects of the student’s writing process served them well, and what practices might they want to change or adopt for the next assignment?
• As they begin work on the next assignment, ask students to consider what they learned writing the last one. What ideas from that project will inform this one? What lessons about their own writing process did they learn, and how will that inform the way they write this assignment?

None of these techniques are particularly novel, but they are powerful, because they require students to consider not just the final product of the assignment, but the actual learning process that the assignment is designed to enact.  It seems obvious to us that we create writing assignments because we want students to learn from the process of writing them, but students tend to fixate on the product rather than the process.  This makes the actual work of writing seem obscure and magical, even when they do it themselves. They sit down at the computer, mull over the topic at hand, and gradually, sometimes painfully, the final product grinds itself into being.  When they’re asked to articulate these steps in writing, though, their process becomes visible to them, and the opportunity emerges for them to critically examine what they do and how they can do it better.

Their writing process also becomes more visible to you, which is useful both instructionally and in the context of making assignments AI-resistant.  In instructional terms, metacognitive writing allows you to respond to the way students work, not just the work itself.  You can see how their ideas evolve and, ideally, help to guide them.  You can see how students approach writing (from methodologies of research to basic time management) and offer encouragement or guidance.  In other words, you can make their learning an active part of the class.

This pushes against the encroachment of AI in a number of ways.  Most concretely, any of the metacognitive steps suggested above could be completed effectively in class, making it much harder (though perhaps not impossible) for students to covertly hand the work over to the robot.  Furthermore, if students know that they’ll have to explain their writing process in some detail, they might think twice about letting AI do the writing.  None of the tasks suggested above should be particularly challenging for students who actually completed the assignment as designed, but they’re considerably more challenging as exercises in creative fiction.  Pointing this out to students when you introduce the assignment can reduce the perceived benefits of letting AI do the heavy lifting.

On a less concrete but more profound level, though, this kind of scaffolding discourages AI-based cheating by placing value on the writing process rather than just the product.  By helping students see how the real intellectual labor called for by your assignment is meant to benefit them, you discourage the transactional mentality that sees assignments essentially as invoices for students to fill.  My experience is that the overwhelming majority of students are more willing to work than we tend to assume, as long as they believe that their efforts will be rewarded in some way, and metacognitive writing can help them see the benefits of their work in a useful and tangible form.

The same can really be said for any of the practices described above. At the end of the day, we cannot force students to feel invested in their educations, nor can we stop them from seeking out ways to make their academic work easier, legitimately or otherwise. However, if we start from the assumption that most students are invested in their education and truly want to learn, and we create assignments that allow them to see and experience that learning as it happens, then the perceived value of letting AI do their writing for them will diminish significantly. It will also allow us, as instructors, to approach AI writing tools from a position of strength by making it a teaching issue rather than a detection and enforcement issue.

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• Using ChatGPT for Assignments | Tips & Examples

Using ChatGPT for Assignments | Tips & Examples

Published on 13 February 2023 by Jack Caulfield and Tobias Solis. Revised on 15 May 2023.

People are still figuring out the best use cases for ChatGPT , the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use the tool to assist with your academic writing .

ChatGPT can assist you with the following steps when writing a paper, thesis , or dissertation :

• Developing a research question
• Creating an outline
• Generating literature ideas

Paraphrasing text

• Getting feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Developing a research question with chatgpt, creating an outline of your paper with chatgpt, generate literature ideas, getting feedback from chatgpt, limitations of chatgpt, other interesting articles, frequently asked questions about using chatgpt for assignments.

You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.

With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.

However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).

First input

Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”

ChatGPT output

• To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviours?
• How does the personalised algorithm of social media platforms shape the formation of political opinions among its users?
• What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analysed?

Second input

Based on the second research question, develop three further research questions on the topic of polarisation in UK politics.

• Build my scientific method, qualitative discourse analysis, into each question
• Include the term “filter bubble” in each question
• How does the filter bubble effect on social media platforms contribute to the polarisation of political attitudes in the UK? A qualitative discourse analysis.
• What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK? A qualitative discourse analysis.
• How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the UK? A qualitative discourse analysis.

Third input

Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.

• How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarisation of political attitudes in the UK?
• What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK?
• How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the UK?

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

You can also use ChatGPT to help you draft a research paper outline or thesis outline . To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.

However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.

You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.

Create an outline for an academic research paper with the following research question:

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”

The paper will be about 8 pages long.

• Background information on filter bubbles and political echo chambers
• Purpose of the study
• Research question
• Thesis statement
• Definition and concept of filter bubbles
• Definition and concept of political echo chambers
• Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Critiques and limitations of previous studies
• Research design
• Participants
• Data collection and analysis
• Validity and reliability
• Findings from qualitative discourse analysis
• Results related to the research question
• Implications of the findings
• Interpretation of the results
• Comparison with previous studies
• Limitations of the study
• Implications for future research
• Summary of the results
• Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Conclusion and recommendations for future research
• List of references used in the paper
• Data collection materials
• Examples of qualitative data analysis

This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?

• Background on filter bubbles and political echo chambers
• Definition of filter bubbles and political echo chambers
• Previous studies on the role of filter bubbles
• Limitations of previous studies
• Implications for understanding the role of filter bubbles
• Final thoughts

ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.

However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.

What types of sources could I use to write a paper on the following research question?

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK?”

When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK, you could use the following types of sources:

• Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
• Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
• Government reports and studies: Government agencies may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
• News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
• Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
• Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the UK can be useful in providing evidence to support your arguments.
• Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.

You can also try using ChatGPT to paraphrase text. ChatGPT can quickly generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.

This kind of paraphrasing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The paraphrases often:

• Contain grammatical errors
• Include false information

So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources .

An alternative is to use the Scribbr Paraphrasing Tool , which was designed directly for this purpose.

Paraphrase the following text:

“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behaviour on the site. It results in the user only being presented with information that confirms their biases.”

Restructure the sentences and use other phrasings for the following parts:

• “results from”
• “only being presented with”

“A filter bubble is created when a social media algorithm customises its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.” Note We strongly advise against having ChatGPT write text for you and trying to pass it off as your own work. This is academically dishonest and is widely considered plagiarism . It will usually result in an automatic fail, as well as other potential consequences .

You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.

An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.

This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.

If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service .

[Text you want to get feedback on.]

Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:

Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”

Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”

Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.

Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:

No original research

Risk of plagiarism, fake sources, fake “facts”.

ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.

Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.

Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.

Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.

ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.

In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator .

ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.

Instead, its responses are based on recognising and reproducing patterns that it has seen in other texts. This means that if it doesn’t “know” something, it tends to guess. And its guesses are presented with full confidence, just like established facts.

So it’s very important that you carefully check any factual claims made by ChatGPT against more credible sources —and don’t cite ChatGPT as a source of factual information for your research.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, ChatGPT is able to create code in different programming languages like Python, Java and C++.

There are several ways you can use ChatGPT in your studies , such as if programming is part of your bachelor’s or master’s degree.

You should not trust ChatGPT’s results unconditionally. While you can use ChatGPT during your studies to clarify questions, you should always double-check the answers you receive against other credible sources , as it doesn’t always give correct information. Don’t cite ChatGPT as a source of factual information.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Caulfield, J. & Solis, T. (2023, May 15). Using ChatGPT for Assignments | Tips & Examples. Scribbr. Retrieved 2 April 2024, from https://www.scribbr.co.uk/using-ai-tools/using-chatgpt-for-assignments/

Is this article helpful?

Jack Caulfield

Other students also liked, how to use chatgpt in your studies, academic integrity vs academic dishonesty, applying the craap test & evaluating sources, still have questions.

Closed through July 6

Reopening July 7 Tuesday through Thursday 10 AM -2 PM

Complete Hours

Ai in the classroom.

• AI & Critical Pedagogy

AI-Proof Assignments

• AI Assignment Examples
• How to cite ChatGPT
• Further Reading

Remix & Share

Many traditional assessment strategies, such as papers and online essay exams, are particularly easy to outsource with generative AI. However, below are several strategies you can use to mitigate the risk that students will fully outsource their work.

Alternatively, you can also create assessments that intentionally use AI. See AI Assignment Examples for ideas.

You may also want to add specific language to your syllabus indicating that using a chatbot in your course will be considered cheating and/or plagiarism.

• Goodbye, 5-¶ Essay
• Collaborative Learning & Discussions
• Multimodal Demonstrations of Learning
• Brain Dumps
• Explain Your Thinking
• Niche Content
• Field Observations

Move away from the five-paragrah essay format. Gen AI can follow this format easily. Encourage your students' originality by moving away from this formulaic format.

Tip: If you want to stick with the five-paragraph essay, test out your prompt on an advanced AI tool like ChatGPT. Greene (2022) writes, "If it can come up with an essay that you would consider a good piece of work, then that prompt should be refined, reworked, or simply scrapped... if you have come up with an assignment that can be satisfactorily completed by computer software, why bother assigning it to a human being?"

Sticking with essays? Warner (2022) suggests focusing on process rather than product. Scaffolding learning and allowing students to explain their thinking and make learning visible along the way are strategies that may help you confirm student originality. Warner's philosophy aligns with that at Butler University: " I talk to the students, one-on-one about themselves, about their work. If we assume students want to learn - and I do - we should show our interest in their learning, rather than their performance."

In the short-term, you can have your students write essays in class and on paper. 

This isn't a good long-term solution for a few reasons:

• For longer research papers, students will have access to chatbots outside of class.
• Students may need to use online resources for their writing.
• You won't be able to use the LMS feedback tools for annotation, rubric scoring, and grading.

Note: Some students may have accommodations to type their work rather than handwrite it. Make sure to follow student accommodations when assigning work. 

Idea from Ditch That Textbook

Using collaborative activities and discussions is one strategy to mitigate the use of gen AI responses in your class. While students may generate ideas from an AI tool, they will need to discuss with one another whether they want to use the tool's responses, if they fit the prompt, and if they are factually accurate.

Activities to try include:

• Think-Pair-Share
• Fishbowl Discussions
• Brainstorming with physical sticky notes or Padlet
• 10 Discussion Strategies to Use in Class Tomorrow  (Ditch That Textbook)
• Creating Podcasts or Videos

Idea from  Ditch That Textbook

Engage your students in meaning-making activities to demonstrate their learning.

Consider low-tech activities like:

• Drawings and sketches
• Concept Mapping
• Fun formative assessment: 12 easy, no-tech ideas   (Ditch That Textbook)

Consider technology-infused activities like:

• Infographics*
• Digital Storytelling*
• Drawings and sketches using Google Drawings or Jamboard
• Let students choose a medium and activity  (“Digital Media Design Student Choice Board” by Torrey Trust is licensed under CC BY NC SA 4.0 )
• Write* or revise Wikipedia articles (Wiki Education)

* Note that an AI tool can provide an outline for these activities.

Brain dumps are an ungraded recall strategy. The practice involves pausing a lecture and asking students to write everything they can recall about a specific topic. Read more at:

• Brain Dump: A small strategy with a big impact (Retrieval Practice)

During or after writing, students explain their process or thinking. Students could:

• Use Comments in Word or Google Docs;
• Create a video explaining their change history on a Google Doc;
• Use Track Changes to show their revisions.

Ideas were inspired by Watkins (2022).

Consider using planned or impromptu oral exams. You may consider including phrasing in your syllabus about conducting oral exams if you suspect plagiarism through the use of a chatbot.

Idea from Darren Hudson Hick (2022).

When selecting readings, consider sourcing more obscure texts for your students to read. AI may have less information in their training data on obscure texts. As an example, the New York Times reports that, "Frederick Luis Aldama, the humanities chair at the University of Texas at Austin, said he planned to teach newer or more niche texts that ChatGPT might have less information about, such as William Shakespeare’s early sonnets instead of 'A Midsummer Night’s Dream'" (Huang, 2023). 

Contact a Wabash librarian for help sourcing new content.

(Note that ChatGPT is currently trained on data through 2021. Some educators suggest using newer writings and research, but this strategy isn't foolproof since the training models for chatbots are updated frequently.)

Coordinate times to take your class to conduct field observations; students can note their observations and write a reflection about their experience.

Idea from Kelley (2023)

Detecting Work Produced by AI

Can turnitin detect ai-written essays.

Currently Turnitin  cannot  detect content written by AI. Watch the video below for an example of Turnitin scores against 20 Chat GPT essay with the same prompt.

What AI detection tools can I use as an instructor?

Although some AI detection tools exist, we do not currently recommend using these. Current AI detection tools have a low rate of accuracy and produce false positives, especially for content written by non-native English writers. Instead, we recommend using the above strategies to mitigate the risks that students will outsource their work to AI or incorporate AI activities in your teaching.

Aaronson, S. (2022, November 28).  My AI safety lecture for UT Effective Altruism . Shtetl-Optimized: The blog of Scott Aaronson. Retrieved on January 11, 2023, from  https://scottaaronson.blog/?p=6823 . 

Bowman, E. (2023, January 9).  A college student created an app that can tell whether AI wrote an essay . NPR. Retrieved on January 10, 2023, from  https://www.npr.org/2023/01/09/1147549845/gptzero-ai-chatgpt-edward-tian-plagiarism

Caren, C. (2022, December 15).  AI writing: The challenge and opportunity in front of education now . Turnitin. Retrieved on January 10, 2023, from  https://www.turnitin.com/blog/ai-writing-the-challenge-and-opportunity-in-front-of-education-now

Chechitelli, A. (2023, January 13). Sneak preview of Turnitin’s AI writing and ChatGPT detection capability. Turnitin. Retrieved on January 17, 2023, from  https://www.turnitin.com/blog/sneak-preview-of-turnitins-ai-writing-and-chatgpt-detection-capability

Ditch That Textbook. (2022, December 17).  ChatGPT, chatbots and artificial intelligence in education . Retrieved on January 6, 2023, from  https://ditchthattextbook.com/ai/

Hick, D.H. (2022, December 15).  Today, I turned in the first plagiarist I’ve caught using A.I. software to write her work [Facebook post]. Facebook. Retrieved on January 10, 2023, from  https://www.facebook.com/title17/posts/pfbid0D8i4GuCUJeRsDJjM1JJtfkDYDMCb7Y7RdK2EoyVhRuctg9z2fhvpo1bB2WAxGBzcl

Huang, K. (2023, January 16).  Alarmed by A.I. chatbots, universities start revamping how they teach . The New York Times. Retrieved on January 17, 2023, from  https://www.nytimes.com/2023/01/16/technology/chatgpt-artificial-intelligence-universities.html

Greene, P. (2022, December 11).  No, ChatGPT is not the end of high school english. But here’s the useful tool it offers teachers . Forbes. Retrieved on January 9, 2023, from  https://www.forbes.com/sites/petergreene/2022/12/11/no-chatgpt-is-not-the-end-of-high-school-english-but-heres-the-useful-tool-it-offers-teachers

Kelley, K.J. (2023, January 19).  Teaching Actual Student Writing in an AI World . Inside Higher Ed. Retrieved on January 19, 2023, from  https://www.insidehighered.com/advice/2023/01/19/ways-prevent-students-using-ai-tools-their-classes-opinion

Warner, J. (2022, December 11). ChatGPT can't kill anything worth preserving: If an algorithm is the death of high school English, maybe that's an okay thing. The Biblioracle Recommends. Retrieved on January 11, 2023, from  https://biblioracle.substack.com/p/chatgpt-cant-kill-anything-worth

Watkins, R. (2022, December 18).  Update your course syllabus for chatGPT . Medium. Retrieved on January 6, 2023, from  https://medium.com/@rwatkins_7167/updating-your-course-syllabus-for-chatgpt-965f4b57b003

Wiggers, K. (2022, Decemer 10).  OpenAI’s attempts to watermark AI text hit limits . TechCrunch. Retrieved on January 10, 2023, from  https://techcrunch.com/2022/12/10/openais-attempts-to-watermark-ai-text-hit-limits/

• << Previous: AI & Critical Pedagogy
• Next: AI Assignment Examples >>
• Last Updated: Oct 18, 2023 9:54 AM
• URL: https://library.wabash.edu/ai-in-the-classroom

Lilly Library is a founding member of PALNI , ALI , and The Oberlin Group

AI in the Classroom

• Chatbots & Critical Pedagogy
• Chatbots & Accessibility

Chatbot-Proof Assignments

• Chatbot Assignment Examples
• How to cite ChatGPT
• Tutorial: AI, ChatGPT, and Responsible Use for Coursework

Kristen Palmer

Jeana Jorgensen

Remix & Share

While there may not be completely chatbot-proof assignments, try some of the strategies listed below to mitigate the use of chatbots by students in your course.

You may also want to add specific language to your syllabus indicating that using a chatbot in your course will be considered cheating and/or plagiarism.

• Goodbye, 5-¶ Essay
• Collaborative Learning & Discussions
• Multimodal Demonstrations of Learning
• Brain Dumps
• Explain Your Thinking
• Niche Content
• Field Observations

Move away from the five-paragrah essay format. Chatbots can follow this format easily. Encourage your students' originality by moving away from this formulaic format.

Tip: If you want to stick with the five-paragraph essay, test out your prompt on an advanced chatbot like ChatGPT. Greene (2022) writes, "If it can come up with an essay that you would consider a good piece of work, then that prompt should be refined, reworked, or simply scrapped... if you have come up with an assignment that can be satisfactorily completed by computer software, why bother assigning it to a human being?"

Sticking with essays? Warner (2022) suggests focusing on process rather than product. Scaffolding learning and allowing students to explain their thinking and make learning visible along the way are strategies that may help you confirm student originality. Warner's philosophy aligns with that at Butler University: " I talk to the students, one-on-one about themselves, about their work. If we assume students want to learn - and I do - we should show our interest in their learning, rather than their performance."

In the short-term, you can have your students write essays in class and on paper. 

This isn't a good long-term solution for a few reasons:

• For longer research papers, students will have access to chatbots outside of class.
• Students may need to use online resources for their writing.
• You won't be able to use the LMS feedback tools for annotation, rubric scoring, and grading.

Note: Some students may have accommodations to type their work rather than handwrite it. Make sure to follow student accommodations when assigning work. 

Idea from Ditch That Textbook

Using collaborative activities and discussions is one strategy to mitigate the use of chatbot responses in your class. While students may generate ideas from a chatbot, they will need to discuss with one another whether they want to use the chatbot responses, if they fit the prompt, and if they are factually accurate.

Activities to try include:

• Think-Pair-Share
• Fishbowl Discussions
• Brainstorming with physical sticky notes or Jamboard
• 10 Discussion Strategies to Use in Class Tomorrow  (Ditch That Textbook)
• Creating Podcasts  (Butler LibGuide)

These strategies can work for online courses with a few tweaks. For discussions, ask students to post a recording rather than text. While students may generate a response using ChatGPT, creating their video will require more interaction with the content than copy-pasting a text response would.

Idea from  Ditch That Textbook

Engage your students in meaning-making activities to demonstrate their learning.

Consider low-tech activities like:

• Drawings and sketches
• Concept Mapping
• Fun formative assessment: 12 easy, no-tech ideas   (Ditch That Textbook)

Consider technology-infused activities like:

• Infographics*
• Concept Mapping (Butler LibGuide)
• Digital Storytelling * (Butler LibGuide)
• Drawings and sketches using Google Drawings or Jamboard
• Let students choose a medium and activity  (“Digital Media Design Student Choice Board” by Torrey Trust is licensed under CC BY NC SA 4.0 )
• Write* or revise Wikipedia articles (Wiki Education)

* Note that a chatbot can provide an outline for these activities.

Brain dumps are an ungraded recall strategy. The practice involves pausing a lecture and asking students to write everything they can recall about a specific topic. Read more at:

• Brain Dump: A small strategy with a big impact (Retrieval Practice)

During or after writing, students explain their process or thinking. Students could:

• Use Comments in Word or Google Docs;
• Create a video explaining their change history on a Google Doc;
• Use Track Changes to show their revisions.

Ideas were inspired by Watkins (2022).

Consider using planned or impromptu oral exams. You may consider including phrasing in your syllabus about conducting oral exams if you suspect plagiarism through the use of a chatbot.

Idea from Darren Hudson Hick (2022).

When selecting readings, consider sourcing more obscure texts for your students to read. Chatbots may have less information in their training data on obscure texts. As an example, the New York Times reports that, "Frederick Luis Aldama, the humanities chair at the University of Texas at Austin, said he planned to teach newer or more niche texts that ChatGPT might have less information about, such as William Shakespeare’s early sonnets instead of 'A Midsummer Night’s Dream'" (Huang, 2023). 

Contact your department's librarian for help sourcing new content.

(Note that ChatGPT is currently trained on data through 2021. Some educators suggest using newer writings and research, but this strategy isn't foolproof since the training models for chatbots are updated frequently.)

Coordinate times to take your class to conduct field observations; students can note their observations and write a reflection about their experience.

Idea from Kelley (2023)

Detecting Work Produced by Chatbots

Can turnitin detect chatbot essays.

Currently Turnitin  cannot  detect content written by chatbots. Watch the video below for an example of Turnitin scores against 20 Chat GPT essay with the same prompt.

What chatbot detection tools can I use as an instructor?

Although some chatbot detection tools exist, CAT does not currently recommend using these. We need to further look into these tools and the benefits and harms that they may present to our students and faculty. Three reasons for our hesitation are accuracy, copyright issues, and data and privacy issues.

While CAT has not conducted robust testing, we have submitted some examples of chatbot-produced writings through three common AI detection tools. All three tools have failed to detect chatbot writing in some way. We do not have enough evidence yet to know the false positives and false negatives that these tools may produce. If you use a chatbot detection tool, a fake rating is not enough evidence to accuse a student of cheating or plagiarism; we encourage you to gather additional evidence in the form of alternative assessments like oral exams.

Data & Privacy Issues

Some chatbot detection tools may have privacy policies that violate FERPA or have harmful data collection policies.  For this reason, you will need to scrub any personally identifiable information—and, depending on the tool, use a code, only known to you, to match results with students—before submitting to a detection tool. 

On the Horizon

Turnitin is planning to include detection software in the near future; their website states, "We will incorporate our latest AI writing detection capabilities—including those that recognize ChatGPT writing—into our in-market products for educator use in 2023” (Caren, 2022). Here's a preview of what is in the works (Chechitelli, 2023):

In addition to Turnitin's detection tool, OpenAI, the developer behind ChatGPT, is attempting to add watermarks to ChatGPT output (Wiggers, 2022). If these watermarks can be implemented, there may be new ways to detect ChatGPT output on the horizon. Scott Aaronson (2022), the OpenAI researcher working on watermarking, describes it on his blog post, saying, "Basically, whenever GPT generates some long text, we want there to be an otherwise unnoticeable secret signal in its choices of words, which you can use to prove later that, yes, this came from GPT. We want it to be much harder to take a GPT output and pass it off as if it came from a human." In the post, he goes on to explain mathematically how this is possible. Aaronson points out that there is not regulation for AI safety, so there is no guarantee that tools coming after ChatGPT will contain similar watermark features.

Aaronson, S. (2022, November 28).  My AI safety lecture for UT Effective Altruism . Shtetl-Optimized: The blog of Scott Aaronson. Retrieved on January 11, 2023, from  https://scottaaronson.blog/?p=6823 . 

Bowman, E. (2023, January 9).  A college student created an app that can tell whether AI wrote an essay . NPR. Retrieved on January 10, 2023, from  https://www.npr.org/2023/01/09/1147549845/gptzero-ai-chatgpt-edward-tian-plagiarism

Caren, C. (2022, December 15).  AI writing: The challenge and opportunity in front of education now . Turnitin. Retrieved on January 10, 2023, from  https://www.turnitin.com/blog/ai-writing-the-challenge-and-opportunity-in-front-of-education-now

Chechitelli, A. (2023, January 13). Sneak preview of Turnitin’s AI writing and ChatGPT detection capability. Turnitin. Retrieved on January 17, 2023, from  https://www.turnitin.com/blog/sneak-preview-of-turnitins-ai-writing-and-chatgpt-detection-capability

Ditch That Textbook. (2022, December 17).  ChatGPT, chatbots and artificial intelligence in education . Retrieved on January 6, 2023, from  https://ditchthattextbook.com/ai/

Hick, D.H. (2022, December 15).  Today, I turned in the first plagiarist I’ve caught using A.I. software to write her work [Facebook post]. Facebook. Retrieved on January 10, 2023, from  https://www.facebook.com/title17/posts/pfbid0D8i4GuCUJeRsDJjM1JJtfkDYDMCb7Y7RdK2EoyVhRuctg9z2fhvpo1bB2WAxGBzcl

Huang, K. (2023, January 16).  Alarmed by A.I. chatbots, universities start revamping how they teach . The New York Times. Retrieved on January 17, 2023, from  https://www.nytimes.com/2023/01/16/technology/chatgpt-artificial-intelligence-universities.html

Greene, P. (2022, December 11).  No, ChatGPT is not the end of high school english. But here’s the useful tool it offers teachers . Forbes. Retrieved on January 9, 2023, from  https://www.forbes.com/sites/petergreene/2022/12/11/no-chatgpt-is-not-the-end-of-high-school-english-but-heres-the-useful-tool-it-offers-teachers

Kelley, K.J. (2023, January 19).  Teaching Actual Student Writing in an AI World . Inside Higher Ed. Retrieved on January 19, 2023, from  https://www.insidehighered.com/advice/2023/01/19/ways-prevent-students-using-ai-tools-their-classes-opinion

Warner, J. (2022, December 11). ChatGPT can't kill anything worth preserving: If an algorithm is the death of high school English, maybe that's an okay thing. The Biblioracle Recommends. Retrieved on January 11, 2023, from  https://biblioracle.substack.com/p/chatgpt-cant-kill-anything-worth

Watkins, R. (2022, December 18).  Update your course syllabus for chatGPT . Medium. Retrieved on January 6, 2023, from  https://medium.com/@rwatkins_7167/updating-your-course-syllabus-for-chatgpt-965f4b57b003

Wiggers, K. (2022, Decemer 10).  OpenAI’s attempts to watermark AI text hit limits . TechCrunch. Retrieved on January 10, 2023, from  https://techcrunch.com/2022/12/10/openais-attempts-to-watermark-ai-text-hit-limits/

• << Previous: Chatbots & Accessibility
• Next: Chatbot Assignment Examples >>
• Last Updated: Oct 26, 2023 2:30 PM
• URL: https://libguides.butler.edu/ai-in-the-classroom

QUICK LINKS

Library Hours Study Rooms My Library Account Library Website

Ohio State nav bar

The Ohio State University

• BuckeyeLink
• Find People
• Search Ohio State

AI Teaching Strategies: Transparent Assignment Design

The rise of generative artificial intelligence (AI) tools like ChatGPT, Google Bard, and Jasper Chat raises many questions about the ways we teach and the ways students learn. While some of these questions concern how we can use AI to accomplish learning goals and whether or not that is advisable, others relate to how we can facilitate critical analysis of AI itself. 

The wide variety of questions about AI and the rapidly changing landscape of available tools can make it hard for educators to know where to start when designing an assignment. When confronted with new technologies—and the new teaching challenges they present—we can often turn to existing evidence-based practices for the guidance we seek.

This guide will apply the Transparency in Learning and Teaching (TILT) framework to "un-complicate" planning an assignment that uses AI, providing guiding questions for you to consider along the way. 

The result should be an assignment that supports you and your students to approach the use of AI in a more thoughtful, productive, and ethical manner.    

Plan your assignment.

The TILT framework offers a straightforward approach to assignment design that has been shown to improve academic confidence and success, sense of belonging, and metacognitive awareness by making the learning process clear to students (Winkelmes et al., 2016). The TILT process centers around deciding—and then communicating—three key components of your assignment: 1) purpose, 2) tasks, and 3) criteria for success. 

Step 1: Define your purpose.

To make effective use of any new technology, it is important to reflect on our reasons for incorporating it into our courses. In the first step of TILT, we think about what we want students to gain from an assignment and how we will communicate that purpose to students.

The  SAMR model , a useful tool for thinking about educational technology use in our courses, lays out four tiers of technology integration. The tiers, roughly in order of their sophistication and transformative power, are S ubstitution, A ugmentation, M odification, and R edefinition. Each tier may suggest different approaches to consider when integrating AI into teaching and learning activities. 

Questions to consider:

• Do you intend to use AI as a substitution, augmentation, modification, or redefinition of an existing teaching practice or educational technology?
• What are your learning goals and expected learning outcomes?
• Do you want students to understand the limitations of AI or to experience its applications in the field? 
• Do you want students to reflect on the ethical implications of AI use?  

Bloom’s Taxonomy is another useful tool for defining your assignment’s purpose and your learning goals and outcomes. 

This downloadable Bloom’s Taxonomy Revisited resource , created by Oregon State University, highlights the differences between AI capabilities and distinctive human skills at each Bloom's level, indicating the types of assignments you should review or change in light of AI. Bloom's Taxonomy Revisited is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).  

Access a transcript of the graphic .

Step 2: Define the tasks involved.

In the next step of TILT, you list the steps students will take when completing the assignment. In what order should they do specific tasks, what do they need to be aware of to perform each task well, and what mistakes should they avoid? Outlining each step is especially important if you’re asking students to use generative AI in a limited manner. For example, if you want them to begin with generative AI but then revise, refine, or expand upon its output, make clear which steps should involve their own thinking and work as opposed to AI’s thinking and work.

• Are you designing this assignment as a single, one-time task or as a longitudinal task that builds over time or across curricular and co-curricular contexts?  For longitudinal tasks consider the experiential learning cycle (Kolb, 1984) . In Kolb’s cycle, learners have a concrete experience followed by reflective observation, abstract conceptualization, and active experimentation. For example, students could record their generative AI prompts, the results, a reflection on the results, and the next prompt they used to get improved output. In subsequent tasks students could expand upon or revise the AI output into a final product. Requiring students to provide a record of their reflections, prompts, and results can create an “AI audit trail,” making the task and learning more transparent.
• What resources and tools are permitted or required for students to complete the tasks involved with the assignment? Make clear which steps should involve their own thinking (versus AI-generated output, for example), required course materials, and if references are required. Include any ancillary resources students will need to accomplish tasks, such as guidelines on how to cite AI , in APA 7.0 for example.
• How will you offer students flexibility and choice? As of this time, most generative AI tools have not been approved for use by Ohio State, meaning they have not been  vetted for security, privacy, or accessibility issues . It is known that many platforms are not compatible with screen readers, and there are outstanding questions as to what these tools do with user data. Students may have understandable apprehensions about using these tools or encounter barriers to doing so successfully. So while there may be value in giving students first-hand experience with using AI, it’s important to give them the choice to opt out. As you outline your assignment tasks, plan how to provide alternative options to complete them. Could you provide AI output you’ve generated for students to work with, demonstrate use of the tool during class, or allow use of another tool that enables students to meet the same learning outcomes.

Microsoft Copilot is currently the only generative AI tool that has been vetted and approved for use at Ohio State. As of February 2024, the Office of Technology and Digital Innovation (OTDI) has enabled it for use by students, faculty, and staff. Copilot is an AI chatbot that draws from public online data, but with additional security measures in place. For example, conversations within the tool aren’t stored. Learn more and stay tuned for further information about Copilot in the classroom.

• What are your expectations for academic integrity? This is a helpful step for clarifying your academic integrity guidelines for this assignment, around AI use specifically as well as for other resources and tools. The standard Academic Integrity Icons in the table below can help you call out what is permissible and what is prohibited. If any steps for completing the assignment require (or expressly prohibit) AI tools, be as clear as possible in highlighting which ones, as well as why and how AI use is (or is not) permitted.

Promoting academic integrity

While inappropriate use of AI may constitute academic misconduct, it can be muddy for students to parse out what is permitted or prohibited across their courses and across various use cases. Fortunately, there are existing approaches to supporting academic integrity that apply to AI as well as to any other tool. Discuss academic integrity openly with students, early in the term and before each assignment. Purposefully design your assignments to promote integrity by using real-world formats and audiences, grading the process as well as the product, incorporating personal reflection tasks, and more. 

Learn about taking a proactive, rather than punitive, approach to academic integrity in A Positive Approach to Academic Integrity.

Step 3: Define criteria for success.

An important feature of transparent assignments is that they make clear to students how their work will be evaluated. During this TILT step, you will define criteria for a successful submission—consider creating a  rubric to clarify these expectations for students and simplify your grading process. If you intend to use AI as a substitute or augmentation for another technology, you might be able to use an existing rubric with little or no change. However, if AI use is modifying or redefining the assignment tasks, a new grading rubric will likely be needed. 

• How will you grade this assignment? What key criteria will you assess? 
• What indicators will show each criterion has been met? 
• What qualities distinguish a successful submission from one that needs improvement? 
• Will you grade students on the product only or on aspects of the process as well? For example, if you have included a reflection task as part of the assignment, you might include that as a component of the final grade.

Alongside your rubric, it is helpful to prepare examples of successful (and even unsuccessful) submissions to provide more tangible guidance to students. In addition to samples of the final product, you could share examples of effective AI prompts, reflections tasks, and AI citations. Examples may be drawn from previous student work or models that you have mocked up, and they can be annotated to highlight notable elements related to assignment criteria. 

Present and discuss your assignment.

As clear as we strive to be in our assignment planning and prompts, there may be gaps or confusing elements we have overlooked. Explicitly going over your assignment instructions—including the purpose, key tasks, and criteria—will ensure students are equipped with the background and knowledge they need to perform well. These discussions also offer space for students to ask questions and air unanticipated concerns, which is particularly important given the potential hesitance some may have around using AI tools. 

• How will this assignment help students learn key course content, contribute to the development of important skills such as critical thinking, or support them to meet your learning goals and outcomes? 
• How might students apply the knowledge and skills acquired in their future coursework or careers? 
• In what ways will the assignment further students’ understanding and experience around generative AI tools, and why does that matter?
• What questions or barriers do you anticipate students might encounter when using AI for this assignment?

As noted above, many students are unaware of the accessibility, security, privacy, and copyright concerns associated with AI, or of other pitfalls they might encounter working with AI tools. Openly discussing AI’s limitations and the inaccuracies and biases it can create and replicate will support students to anticipate barriers to success on the assignment, increase their digital literacy, and make them more informed and discerning users of technology. 

Explore available resources It can feel daunting to know where to look for AI-related assignment ideas, or who to consult if you have questions. Though generative AI is still on the rise, a growing number of useful resources are being developed across the teaching and learning community. Consult our other Teaching Topics, including AI Considerations for Teaching and Learning , and explore other recommended resources such as the Learning with AI Toolkit and Exploring AI Pedagogy: A Community Collection of Teaching Reflections.

If you need further support to review or develop assignment or course plans in light of AI, visit our Help forms to request a teaching consultation .

Using the Transparent Assignment Template

Sample assignment: ai-generated lesson plan.

In many respects, the rise of generative AI has reinforced existing best practices for assignment design—craft a clear and detailed assignment prompt, articulate academic integrity expectations, increase engagement and motivation through authentic and inclusive assessments. But AI has also encouraged us to think differently about how we approach the tasks we ask students to undertake, and how we can better support them through that process. While it can feel daunting to re-envision or reformat our assignments, AI presents us with opportunities to cultivate the types of learning and growth we value, to help students see that value, and to grow their critical thinking and digital literacy skills. 

Using the Transparency in Learning and Teaching (TILT) framework to plan assignments that involve generative AI can help you clarify expectations for students and take a more intentional, productive, and ethical approach to AI use in your course. 

• Step 1: Define your purpose. Think about what you want students to gain from this assignment. What are your learning goals and outcomes? Do you want students to understand the limitations of AI, see its applications in your field, or reflect on its ethical implications? The SAMR model and Bloom's Taxonomy are useful references when defining your purpose for using (or not using) AI on an assignment.
• Step 2: Define the tasks involved. L ist the steps students will take to complete the assignment. What resources and tools will they need? How will students reflect upon their learning as they proceed through each task?  What are your expectations for academic integrity?
• Step 3: Define criteria for success. Make clear to students your expectations for success on the assignment. Create a  rubric to call out key criteria and simplify your grading process. Will you grade the product only, or parts of the process as well? What qualities indicate an effective submission? Consider sharing tangible models or examples of assignment submissions.

Finally, it is time to make your assignment guidelines and expectations transparent to students. Walk through the instructions explicitly—including the purpose, key tasks, and criteria—to ensure they are prepared to perform well.

• Checklist for Designing Transparent Assignments
• TILT Higher Ed Information and Resources

Winkelmes, M. (2013). Transparency in Teaching: Faculty Share Data and Improve Students’ Learning. Liberal Education 99 (2).

Wilkelmes, M. (2013). Transparent Assignment Design Template for Teachers. TiLT Higher Ed: Transparency in Learning and Teaching. https://tilthighered.com/assets/pdffiles/Transparent%20Assignment%20Templates.pdf

Winkelmes, M., Bernacki, M., Butler, J., Zochowski, M., Golanics, J., Weavil, K. (2016). A Teaching Intervention that Increases Underserved College Students’ Success. Peer Review.

Related Teaching Topics

Ai considerations for teaching and learning, ai teaching strategies: having conversations with students, designing assessments of student learning, search for resources.

Artificial Intelligence and Assignment Design

Generative ai assignments.

There are both academic and practical reasons you may choose to incorporate generative AI assignments into your course. For example, you may believe that AI will be a skill needed in the students’ future careers in your field. Perhaps you see AI as a tool to help students deepen their understanding of and engagement with your content. You may see the introduction of AI into your classroom as a way to open a conversation about its ethical and academic implications. Integrating AI ironically allows instructors to think deeply about how to design assignments that cannot be easily generated by AI alone to deter plagiarism and cheating. This guide comes from the perspective that you are open to developing AI assignments.

Note, it is critical to develop AI policies for your course along with policies for specific AI assignments.

Considerations for Developing an AI Assignment

Alignment with your course goals.

In the development of AI assignments, the primary consideration is whether the use of AI will help your students achieve the learning goals of the course. Ask yourself, does this assignment help student gain skills and knowledge central to your course and field? Furthermore, consider whether the assignment is engaging enough to warrant incorporating AI. Are you asking students to go above and beyond the AI-generated content? An impactful assignment will challenge students to transform, expand upon, correct, or critique the information and content generated by AI or learning about themselves in relationship to AI. Educational pedagogy expert Derek Bruff gives further insight into how to think about AI assignments as they relate to course design in his blog post about AI and writing assignments .

Guidelines for Use

If you integrate AI into your assignments, be sure to discuss your expectations with your students. It is essential that they understand why you have decided to allow AI in the course and its role in their learning. Furthermore, students can be engaged in wider conversations about AI and its personal impact on their lives. The University of Calgary has developed a set of recommendations of how to start these conversations. One strategy is writing a code of conduct that emphasizes critical thinking and sets guardrails of proper use. You can provide a prewritten list of guidelines or work with the students from scratch by posing questions about AI and learning.

For example, the class may have guidelines such as:

• We will only use AI to help our intellectual development, not replace it.
• We will be transparent in our use of AI.
• We will not submit AI generated text without attribution.
• We will follow guidelines of when AI is appropriate to use.

Assignment Mechanics

Detailed instructions for an AI assignment will raise the chances for a successful learning experience. Students are not familiar with the processes of this novel type of intellectual work, and thinking through the different facets of the activity will help you to execute and evaluate the assignment confidently. Consider the following questions:

• Are you allowing ample time to complete the assignment considering it is a new tool for students?
• Is it better to do the assignment together in class or out of class?
• Have you practiced using the technology together?
• How should AI be cited? Are there specific steps for showing how the original AI text is changed?
• What kind of prompts are allowed? What functions can AI be used for?
• How will you provide feedback on their use of AI?

AI Literacy

Both you and your students should have a level playing field when it comes to understanding generative AI. You cannot count on students to understand the pitfalls and limitations of AI or even how to use the tools. There are existing resources on AI literacy developed specifically for students that can be a starting point. This library guide from the University of Arizona instructs students on AI, plus there is a companion guide for instructors as well.

Ethical Concerns

There are ethical issues to using AI beyond questions of plagiarism, copyright and academic integrity that should be considered. First, to minimize threats to the privacy of your students and yourself, personal information should not be shared. To dive deeper into privacy concerns, speak with students about the implications of AI services using our data to train their tools.

Second, students may not have equal access to the internet or sufficient funds for subscriptions to AI tools. Be sure to suggest several different AI tools and confirm that students are able to access at least one tool without paying for it. Not all students may take to generative AI equally and will not have the skills to architect effective prompts for your discipline or type of assignment. You can support them by modeling prompt generation or forming groups in class that can work together with AI.

Finally, for instructors who do allow AI for learning, there should be considerations for students who do not want to use it on ethical grounds. This could be solved by making AI assignments low-stakes or optional.

Types of Generative AI Assignments

Below are some general ideas of how to incorporate AI into your course. We encourage you to seek out examples from your discipline or related to the core skills of your course. Some resources worth exploring are ChatGPT asssignments to use in your classroom today (an open source book from the University of Central Florida) and a publication on coding and generative AI by an international group of computer science instructors. Instructors may also wish to leverage generative AI to help with routine tasks and lesson planning .

Brainstorming Ideas and Defining Concepts

Generative AI excels at summarizing content and explaining concepts. Warning to students, it is not necessarily 100% correct!

• Users can ask AI to brainstorm research questions. “What are some examples of bank failures due to fractional reserve banking ?” Or, “What are some of the major events of the Cold War?”
• Users can ask AI for clarification of concepts or terms they don’t understand.  “Explain fractional reserve banking in simple terms. ” Or, “What are the Federalist papers and why are they important?”
• Instructors can ask for resources or ideas of how to teach students content.   “Provide an explanation of fractional reserve banking that discusses the pros and cons of its use .” Or, “What are some exercises to do in the classroom to teach the lifecycle of a butterfly?”

Writing Assistance

While it is possible to use generative AI to correct an entire essay, students can be instructed to prompt AI to provide limited feedback on specific aspects of their writing. Prompts could be limited in scope. For example, students can ask AI to:

• Rate the clarity of an argument “How well did I explain X? ” Or, “Does this writing contain all of the standard sections of a case study ?”
• Suggest alternatives “Rewrite the conclusion to better summarize the content.” Or, “What is another way to explain this idea?”
• Comment on writing mechanics “Review the sentence structure in this essay.” Or, “Check this essay for passive voice.”
• Provide advice for improvement “List the common grammar mistakes in the essay and provide an explanation of the errors.” Or, “How can I make this writing more upbeat?”

Collaborative Writing

One popular assignment helps instructors show why writing for yourself is important intellectual work. Students read an AI-generated essay and grade it with a rubric. As a class the students discuss its strengths and weaknesses. As a follow-up students can submit a revised essay. In one Yale course, the instructor told students to ask ChatGPT to write its own version of a writing prompt after the students had completed an assignment so they could compare their writing against it.

Another approach to collaboration is to ask AI to write a first draft of an assignment. Students then improve it by doing independent research to double-check the AI content and refining (or rejecting) the AI arguments. Students should record both the questions they asked and the generated text. Students can also be asked to write summaries describing what they learned from the AI search and what they changed. The SPACE framework is a powerful model for organizing these types of writing assignments; the article details the cycle of prompting AI, evaluating its output, and rewriting AI generated content.

Arguably, the greatest strength of generative AI tools may be their ability to write code. Computer scientists are especially concerned about assignments in entry-level programming classes. The way coding is taught may change over time due to AI, but there are short-term strategies that incorporate AI but demand student input. 

• AI could be asked to generate small snippets of code that students integrate into a larger programming project. Students test, debug and refine the code.
• After completing a coding assignment, students prompt AI to write a different implementation of the problem and analyze which is more efficient and why.
• Instructors or students write faulty code and use ChatGPT to generate test cases and/or to fix the errors. 
• Instructors take advantage of AI to generate more coding assignments and review questions for exams.

Two researchers from UC San Diego published the findings of a study about the attitudes of computer scientists to generative AI and possible directions for teaching coding in the future.

ChatGPT and other generative AI tools do not produce expository content only. They are also able to generate content in many creative genres, often with laughable results ( “Write a pop song in the style of Shakespeare” ) The breadth of the kinds of writing generative AI can mimic might provide the chance for humans to use generative AI to spark creativity in themselves. Student might ask AI to describe the life in the Middle Ages from the perspective of a midwife as inspiration to write a modern version, or as background information for writing in another genre. Generative AI can help instructors deliver content in new ways, for example introducing games into teaching. Instructors might ask AI to develop trivia questions for exam review or a game of 20 questions as an in-class activity.

Generative AI can be a coach for learning that supports both instructors and students. Students can easily get more information about what they don’t understand. AI can be an agent for adaptive learning allowing students to “pass” certain learning objectives and get additional practice on concepts and skills they haven’t mastered. By the same token, it can assist instructors who need to provide additional assistance to students and are pressed for time to find resources. Instructors can get ideas for teaching a skill or subject with activity descriptions and lesson plans. AI can generate practice problems or review questions for exam prep, which frees up time for instructors for other class prep.

There are also positive gains in equity when generative AI is used in a tutoring setting. A neurodiverse student may find conversations with a bot to be non-judgmental and less stressful when needing help. Non-native speakers can ask for word and concept definitions to level up their understanding of course content and context. The review and tutoring capabilities of AI can help all students to practice concepts and receive feedback on their progress.

Looking Ahead

Incorporating generative AI into education is not without peril. Students’ reliance on AI content could potentially lead to losing skills in academic writing. There is the risk that students might mistakenly believe that AI is inherently better at developing ideas and expressing information; leaving students uncomfortable adding their own voice to writing. Without training on how to check the validity of AI content and conduct independent research, students may miss out on how to evaluate sources and compare ideas.

Like it or not, at this moment it lands on educators to design courses and assignments to mitigate these risks and to have hard and timely conversations with students. It may feel like AI is encroaching on teaching and learning, but we should remember that there are many aspects of teaching that are as important as delivering content. These are skills that only human instructors can perform, such as

• Providing real-time feedback on complex tasks
• Grading or producing subjective or substantive work
• Providing social or emotional support 
• Teaching complex, interconnected concepts
• Engaging in personal interactions

The future of teaching may increasingly focus on those skills that our students need to make sense of their world, engage with others productively and make connections across disciplines and concepts.

General Resources for AI Assignments

A Teacher’s Guide to Prompt ChatGPT , Andrew Herft

AI in the Classroom , UC Riverside

Free AI Writing Resources

Improve your writing with ai.

Improve your academic performance and write like a pro without cheating or jeopardizing your degree. Get access to free AI writing tools, useful ChatGPT prompts, the latest articles about AI, and more.

Start writing

AI tools to help you write with confidence

Paraphrasing Tool

Avoid accidental plagiarism and make your text sound better. Paraphrase now

Grammar Checker

Get instant feedback on your writing. Don’t let typos bring down your grade. Grammar check now

Read more in less time. Distill lengthy and complex texts down to their key points. Summarize now

Detect AI-generated content

Detect AI-generated content like ChatGPT3.5, GPT4 and Google Bard in seconds

Try AI Detector

And fix any mistakes with AI

Scribbr’s AI Proofreader checks your document and corrects spelling, grammar, and punctuation mistakes with near-human accuracy and the efficiency of AI!

Try the new AI Proofreader

ChatGPT prompting 101

ChatGPT can be a great study assistant, but the responses you get are only as good as the input you provide. Keep these four tips in mind to craft great ChatGPT prompts :

• Give ChatGPT a role to play
• Be precise and provide context
• Test and improve your prompts

ChatGPT prompts

100% ethical ChatGPT prompts

Write a research question

• Generate three possible research questions for an argumentative high school essay on the following topic: “The long-term impact of the Covid-19 pandemic.”

Brainstorm topic ideas

• Generate 10 questions to help me brainstorm topics for my college admission essay.

Quiz yourself

• I’m learning about [ insert topic here ]. Please create a practice test with 4 multiple-choice questions, each with 4 possible answers and solutions (show the solutions separately under the multiple-choice test).

Learn by metaphors and stories

• I ‘m learning about [ insert topic here ]. Convert the key lessons from this topic into engaging stories and metaphors to aid my memorization.

Find limitations

• What are some common limitations or critiques of research in the field of [ insert topic here ]?

Learn about a topic

• I want to learn about [ insert topic here ]. Identify and share the most important 20% of learnings from this topic that will help me understand 80% of it. Explain [ insert topic here ] to me without jargon and buzzwords, in the most simplified way possible.

Source recommendations

• What types of sources can I use to write an essay on the following research question? “ [insert research question here] ?”

Overview of arguments

• What are the main arguments or debates in the literature on [ insert topic here ]?

Develop an outline

• Develop an outline for an argumentative high school essay with the following research question: “ [insert research question here] ?”The essay will be about 4 pages long.

Latest articles

Learn more about ai, citing chatgpt, using chatgpt for assignments, how do ai detectors work, using chatgpt in your studies, ai tool reviews.

Best AI Detectors

AI detectors detect text generated by AI tools like ChatGPT. We tested various example texts, including ChatGPT-generated, mixed AI–human, and fully human, as well as text generated by paraphrasing tools. Check out the best AI detectors

Best Paraphrasing Tools

Paraphrasing tools improve your writing by automatically rewriting text. We tested seven popular free and premium paraphrasers to determine their reliability when it comes to producing correct, readable English. Check out the best paraphrasing tools

Best Grammar Checkers

We tested 10 popular free grammar checkers , evaluating their accuracy in fixing errors (and introducing new ones) and user-friendliness. Find out what grammar checker to use

Best summarizers

Summarizers are ideal for distilling lengthy and complicated texts down to their key points—but which summarizers are most accurate? We tested 11 summarizers to find out. Discover the most accurate summarizer

Universities’ policies on AI

Based on our analysis of the top 100 US universities, it appears that the majority haven’t established clear-cut regulations concerning AI tools at this time. As a result, it is up to individual professors to determine what is permissible in their respective courses.

Check out policies in detail

Scribbr's stance on AI

We think educators should be open to the possibilities presented by AI-powered tools. Students should employ these tools in an honest and responsible way, using them to facilitate learning rather than to skip steps in the learning process.

You can use such tools in a responsible way that benefits your education during the research and writing process by relying on them for the following:

• Brainstorming and explore topics in an interactive way
• Assisting with programming and coding
• Developing research questions and paper outlines
• Asking for feedback on your own writing

Write faster, study better – all for free

Five ways to prepare writing assignments in the age of AI

By completing this form, you agree to Turnitin's Privacy Policy . Turnitin uses the information you provide to contact you with relevant information. You may unsubscribe from these communications at any time.

Every day, new articles are published about Artificial Intelligence (AI) and particularly ChatGPT. Every day, educators report on students submitting work assisted or created by AI. Every day, another story pops up about AI tools that have passed the bar exam or an MBA exam in a notoriously rigorous course. We’re in deep now as educators have started to understand the threat, the responsibility, and the promise of AI. Our Turnitin Teaching and Learning team - all former and current educators - is there too, and one thing we’ve learned is that AI isn’t going away… and that’s okay.

More practitioners are beginning to realize that there could be some benefits to AI in education when implemented with intention. It is a balance, though, as not every use of AI tools will support teaching and learning. For example: What if AI is used to replace actual student thinking? What if it’s used to complete an entire assignment? That type of usage is the threat we as educators (yes, I am still teaching!) are working tirelessly to avoid. But WHAT IF there are things we can do to protect our writing assignments against student misuse for classrooms today?

We recently shared guidelines that focused on eleven strategies for approaching AI-generated text in your classroom . Today, we’re going to expand on five specific tactics for educators:

• Update academic integrity policy to inform instruction and assessment practices.
• Communicate new policy and assignment guidelines with students.
• Review and revise writing assignments and associated scoring tools (rubrics, etc.).
• Employ the writing process; live in a formative space.
• Institute opportunities for students to discuss their work.

Notice that these five strategies focus on careful planning and approaching AI proactively. While time is a luxury educators do not have, these tactics may save time later responding to potential AI misuse cases. Let’s dig into the tactics:

How and to what extent is the use of a generative AI tool acceptable within academic environments? Changes to classroom practice rely on answering this question and updating academic integrity policies accordingly. Now is the time to research, discuss, and decide how institutions will respond to the rapidly evolving technology of AI. Our new guide for updating academic integrity policies in the age of AI walks through steps for getting started. We share ideas such as establishing a common lexicon like an AI vocabulary glossary and determining ethical use of AI.

While making institutional changes first is ideal, it may not happen fast enough. Most educators are feeling like they’re already playing catch-up and need tools to respond to AI advances right now. For those educators, we recommend answering the questions for their own classroom even as they work with colleagues and leaders for institutional change. Let’s be agile and develop best practices for AI in our classrooms.

Determining acceptable use of AI will inform changes to instruction and assessment. But what does acceptable use look like? That may vary vastly for each institution, department, classroom, and even assignment, but let’s look at some specific examples. As I suggested earlier, there can be positive benefits for AI in education. Perhaps an educator decides that it’s acceptable for students to use AI writing tools during prewriting (see #3 below) to brainstorm ideas or gain other points of view on a topic. Or maybe the educator decides to allow students to submit a draft to AI to get formative feedback on their work. If educators decide to go down this path, they must choose the right AI tool and personally test it to put parameters in place.

Introduce updated policies to students and talk to them about AI. The policy should be easily accessible to all stakeholders, particularly students. Consider asking students to lead activities to paraphrase policies and present to peers. One valuable exercise that Turnitin advocates have suggested is a classic “This… Not That” activity with scenarios that students can sort/label based on their understanding of the policy. Simply create a list of a few scenarios and have students sort which are acceptable and which are not. The activity itself is fantastic, but what is even more powerful is the discussion around why some uses are acceptable and others are not.

Developing best practices for crafting writing assignments that are resistant to student misuse of AI is imperative. As we’ve all likely read in the media, AI is proficient at some things, but not so proficient at others. If we, as educators, familiarize ourselves with the “answers” from an AI tool, then in theory, we should be able to modify our writing prompts to work around the technology. While this strategy isn’t foolproof, it will certainly help place some of those guardrails.

Let’s take an element that some generative AI writing tools struggle with today. In their current iteration, AI writing tools have been found to list sources that don’t actually exist. When prompted, the tool might provide references, but the sources may be fictitious. Therefore, adding a requirement for students to use verifiable sources with a reference list would help combat this issue. Beyond sources and citations, there’s additional criteria educators can consider when revisiting their assignments. Our team of veteran educators created an AI misuse rubric to help with just that. This rubric proposes four traits: student voice, critical thinking/reasoning, sources and citations, and personalization.

Consider comparing tried and true writing prompts against the rubric. Start by identifying which traits are relevant to an assignment and then assess how the prompt stacks up. Use the weaker areas to consider how it might be modified to better safeguard assignments against AI misuse. The closer a prompt gets to Advanced/Proficient, the less vulnerable to AI misuse it will be.

As a final step, educators should also update their scoring guides or rubrics to reflect new demands of the prompt. Early in my teaching career, a mentor of mine used to say, “Measure what matters most.” As we shift assignment/assessment design, our evaluation tools must be aligned. If scoring guides and rubrics heavily emphasize aspects of writing at which AI tools are skilled, the potential for misuse increases.

The writing process isn’t for novice writers only. Educators everywhere keep hearing how the existence of AI is going to force us to revisit our teaching practices . For those who might have stepped away from implementing the writing process, start there. The writing process isn’t for novice writers only, in part because preparing writing assignments so they include steps like prewriting and drafting will bring visibility to students’ work before a final submission. Leverage that process and require students to submit a draft, leave feedback on their work, and have them make revisions based on the feedback. Creating a writing culture with what feels like open dialogue between student and educator makes it much less likely for students to misuse AI. Additionally, research has proven that specific types of feedback have a quantifiably positive impact on student growth. A portfolio approach is one more way to improve visibility into not only the student’s work, but also their process, all of which adds up to protection against AI misconduct.

Will students use ChatGPT if they must discuss their work with a teacher or classmate? Maybe, but the probability certainly decreases. While requiring discussion may not eliminate the risk, it does provide another guardrail. Plan for assignments to include peer reviews, writing conferences, or reflection assignments live or in video format, creating another layer of visibility and open dialogue. Additionally, if they know they’ll need to share their work, students are often more invested. Not to mention, research shows that having students share their work boosts confidence and motivation toward the task ( Simonsmeier et al., 2020 ).

While not exhaustive, these five strategies can at least serve as a place to begin, and by combining them they have an even greater impact. If educators are unsure where to start exactly, our AI misuse checklist lists these principles (and more!) to help guide them down the path of preparing writing assignments in the age of AI.

• Updating your academic integrity policy in the age of AI
• AI misuse checklist
• AI misuse rubric
• AI vocabulary glossary

•   SMU Libraries
• Scholarship & Research
• Teaching & Learning
• Bridwell Library
• Business Library
• DeGolyer Library
• Fondren Library
• Hamon Arts Library
• Underwood Law Library
• Fort Burgwin Library
• Exhibits & Digital Collections
• SMU Scholar
• Special Collections & Archives
• Connect With Us
• Research Guides by Subject
• How Do I . . . ? Guides
• Find Your Librarian
• Writing Support

Research Assignment Design: Generative AI

• Student Learning Outcomes
• Evaluating Student Work
• Generative AI

Integrating AI

• Demonstrate AI as an idea generator when starting research to map out potential subtopics and related ideas.
• Show how to use AI to get started with research writing, and discuss its flaws.
• Evaluate an AI-written assignment in class, including the information and citations generated.
• Hold an in-class discussion on the ethics of AI, plagiarism, and writing.
• Discuss how to cite AI if used in the research and writing process.

Example AI Assignments

Featured in 101 Creative Ideas to Use AI in Education , these assignments demonstrate ways to integrate AI and information literacy. These have been grouped by lesson, yet each is worth considering.

• Develop critical reading, writing, thinking, and/or evaluation skills (idea numbers 5, 28, 30, 41, 49, 82)
• Spark conversations around the concepts of authorship and citations (idea numbers 17, 41)
• Generate peer review/feedback (idea numbers 32, 68)
• Ask questions of primary sources using ChatPDF (idea number 76)
• 101 Creative Ideas to Use AI in Education

From TextGenEd: Teaching with Text Generation Technologies , get ideas on how to incorporate generative AI with an emphasis on writing. 

• Transforming Writing Assignments with AI  (AI Literacy) 
• Critical Assessment and Analysis Exercise  (AI Literacy)
• Promoting Ethical Artificial Intelligence Literacy  (Ethical Considerations)
• Teaching Social Identity and Cultural Bias Using AI Text Generation  (Ethical Considerations) 
• AI in First Year Writing Courses  (Ethical Considerations)
• Analysis of Iterations of Responses to Human Prompts  (Professional Writing)
• Using AI Text as Prompts for Critical Analysis  (Rhetorical Engagements)

Working around AI

• Design assignments that put the focus on the process of research rather than on the resulting product.
• Incorporate in-class writing or oral assignments.
• Include writing reflections as part of the assignment that speak to a student's specific experience.
• Require the use of class materials such as notes, lectures, and lessons.
• Require direct links to sources in citations.
• Consider using more obscure texts for students to read and use in research.
• Move away from the five paragraph research essay format.
• Consider using low-tech activities (like concept mapping) or high-tech activities (like infographics) to demonstrate knowledge.
• Use field observations in research.
• Have students explain their thinking or their research process through document comments. 

Related Guides and Resources

• Research with Generative AI Best uses for generative AI and conducting secondary research, including recommended tools, ethical considerations, and prompting guidelines
• Artificial Intelligence (AI) Educause Library
• Talking about Generative AI: A Guide for Educators
• << Previous: Evaluating Student Work
• Last Updated: Mar 22, 2024 3:15 PM
• URL: https://guides.smu.edu/research_assignments

Filter by Keywords

10 Educational AI Tools for Students in 2024

Senior Content Marketing Manager

February 13, 2024

AI tools for students are becoming indispensable, from harnessing the power of artificial intelligence to refining writing nuances to getting instantaneous feedback on presentations. 

And the best part? Many of these groundbreaking AI writing tools are not just reserved for the elite—they are accessible and affordable, making them a boon for nonprofits and individuals on a budget. 

Whether you’re looking to craft impeccable essays or master the art of communication, dive in as we explore the top 10 AI-powered tools of 2024 tailored for your academic success.

What Are AI Tools For Students?

How students can best use ai, 2. quillbot, 3. gradescope, 4. otter.ai, 7. audiopen.ai, 9. smart sparrow, 10. wolfram alpha.

AI tools for students refer to various software and applications that utilize artificial intelligence to assist, enhance, or streamline the academic journey. Unlike conventional digital tools, AI-driven tools adapt, predict, and personalize learning experiences based on each student’s individual needs and patterns.

Here’s a breakdown of what they offer:

• Personalized learning: Every student is unique, and the best AI-powered tool can recognize this. They adapt to each student’s pace, learning style, and preferences to deliver tailored content, be it in the form of reading material, quizzes, or tutorials
• Instant feedback: Artificial intelligence education tools can analyze assignments, presentations, and projects, providing real-time feedback. This immediate response helps students understand their areas of improvement without waiting for teacher evaluations
• Productivity enhancements: From organizing study schedules to setting reminders for assignment deadlines, AI tools are equipped to aid students in time management and organization, ensuring they stay on top of their academic tasks
• Interactive learning: AI tools often come with chatbots, virtual assistants, and interactive platforms that make learning engaging and dynamic, breaking the monotony of traditional study methods.
• Data-driven insights: These tools collect and analyze data based on a student’s performance, giving insights into strengths, weaknesses, and potential growth areas, aiding in better academic planning
• Accessibility and Inclusivity: Many AI tools now offer features that make learning accessible for students with disabilities. From voice-to-text functionalities to visual aids, artificial intelligence ensures that education remains inclusive

AI can potentially transform a student’s learning trajectory, but the key lies in effectively harnessing its power. Here’s how students can make the most of AI:

• Setting clear goals: Begin with a clear understanding of what you wish to achieve using SMART goals . Are you looking to improve your essay-writing skills, seeking help with math problems, or aiming to organize your study routine better?
• Blend traditional with technological: AI tools offer unprecedented advantages but’re most effective when combined with traditional learning methods. For instance, after receiving feedback from an AI-powered writing tool, discuss it with a teacher or peer for additional insights
• Engage in interactive learning: Use AI-driven interactive platforms, such as chatbots or virtual tutors. These platforms provide real-time engagement, making complex topics easier to grasp and retain
• Analyze and adapt: Many AI tools provide data-driven insights about your learning patterns. Regularly review these analytics to understand your strengths and areas needing attention
• Ensure data privacy: While using any AI tool, especially those requiring personal data or academic records, ensure that the platform respects user privacy
• Stay open to feedback: One of the hallmarks of AI tools is instant feedback. Critiques, suggestions, or recommendations provided by these tools aim to enhance your skills and understanding
• Stay curious: AI is a fascinating domain with limitless potential. Dive deep, explore its intricacies, and stay curious about how machine learning, neural networks, or natural language processing can further bolster your academic journey

10 Best AI Education Tools in 2024

In 2024, the educational landscape has been transformed by a slew of advanced AI-driven platforms. Here’s a curated list of the 10 best AI education tools leading the charge and revolutionizing learning experiences for students globally.

In the ever-evolving landscape of digital tools, ClickUp has emerged as a front-runner, not just as a conventional project management tool for students but also as an AI-driven powerhouse tailored for student success. Combining the best of organizational features with the prowess of ClickUp Brain , ClickUp is redefining how students approach tasks, projects, and group collaborations.

With ClickUp’s education project management software , students can break down assignments into individual steps, which makes daunting projects more digestible, and then rank those tasks based on urgency and importance so they can focus on what matters most.

ClickUp’s collaborative tools turn group assignments from chore to joy thanks to real-time editing, advanced commenting features, and ClickUp Chat. ClickUp’s AI tools offer productivity analysis that suggests areas of improvement and optimizes your study routine.

ClickUp’s AI Writer and AI Knowledge Manager can help students summarize key information quickly, which is great for analyzing research papers or learning new topics. Using the AI Writer, students can also learn how to write better. They can see examples of good writing and get intelligent tips on improving their own work.

In a nutshell, ClickUp isn’t just another project management tool; it’s a holistic AI platform tailored to fit the unique demands of student life. By leveraging its powerful AI Writer and the intelligence of its AI Knowledge Manager, students can pave the way for academic excellence and a future of seamless project execution.

ClickUp best features

• With ClickUp Tasks, students can organize assignments, projects, and other academic endeavors into manageable chunks
• Automate routine tasks and set up workflows to streamline processes
• All ClickUp Docs , discussions, and tasks are in one place, eliminating the hassle of toggling between multiple apps
• ClickUp seamlessly integrates with various other tools and platforms that students commonly use, like Google Calendar, Drive, and even note-taking apps
• Depending on a student’s preference, they can visualize tasks and projects as a list, on a Kanban-style board, or on a calendar, offering flexibility in project management styles
• Monitor the time spent on different tasks or projects to ensure efficient time allocation
• Never miss a deadline with ClickUp’s robust reminder system. Plus, get yourself organized with the ClickUp Class Schedule and Time Study Template
• With AI enhancements, ClickUp adapts to a student’s work pattern, offering personalized suggestions and insights

ClickUp limitations

• Some users have mentioned that while ClickUp is robust and feature-rich, it can initially come across as overwhelming, especially for those new to project management tools
• While ClickUp’s desktop interface is widely appreciated, a few users have pointed out that the mobile app experience could be more streamlined

ClickUp pricing

• Free Forever
• Unlimited : $7/month per user
• Business : $12/month per user
• Enterprise : Contact for pricing
• ClickUp Brain: Available on all paid plans for $5/Workspace member/month

ClickUp ratings and reviews

• G2 : 4.7/5 (2,000+ reviews)
• Capterra : 4.7/5 (2,000+ reviews)

In an age where crisp, clear, and precise communication is paramount, QuillBot emerges as a beacon for students. A revolutionary AI tool for note-taking , QuillBot is specifically designed to enhance the quality and versatility of written content. 

Its intuitive interface and advanced algorithms make it a must-have for students striving for writing excellence. 

QuillBot acts as a second pair of eyes, helping students refine and elevate the standard of their written assignments and ensuring they make the best impression. Students can significantly expedite the editing and proofreading process with instantaneous suggestions and corrections, saving valuable time.

Knowing that their work has been reviewed and enhanced by a sophisticated AI-powered tool, students can confidently submit their assignments.

Over time, as students continually engage with QuillBot’s suggestions, they can organically improve their writing skills and internalize better writing habits. With its blend of advanced features and user-friendly design, it’s no surprise that many in the academic realm consider Quillbot an essential asset in their writing toolkit.

Quillbot best features

• QuillBot offers a handy browser extension and integrates smoothly with platforms like Google Docs and Microsoft Word
• Students can input sentences or paragraphs and receive alternative versions that retain the original meaning but use different phrasing
• QuillBot offers many modes, including Standard, Fluency, Creative, and more, catering to various writing needs. Each mode provides a different spin on the content, allowing students to find the tone and style that best suits their work.
• QuillBot can suggest synonyms for specific words, aiding students in diversifying their vocabulary and enhancing the richness of their content
• Beyond restructuring sentences, QuillBot offers suggestions to correct grammar mishaps and enhance sentence fluency, ensuring that students’ work is both accurate and articulate

Quillbot limitations

• Though QuillBot is adept at paraphrasing, there are instances where it might not fully grasp or retain the nuanced context of specific sentences, leading to suggestions that might be off-mark. For this reason, some people may prefer a Quillbot alternative
• QuillBot offers both free and premium versions. Some students have noted that the free version, while useful, has limitations regarding word count and access to all features. This might necessitate an upgrade for those requiring extensive use.
• On occasion, QuillBot might lean towards certain synonyms or phrasings more than others, leading to potential vocabulary repetition if not double-checked
• For very intricate or specialized sentences, especially those related to specific academic or scientific topics, QuillBot might occasionally struggle to provide a satisfactory rephrase

Quillbot pricing

• Premium: $19.95/month per user

Quillbot ratings and reviews

• Capterra: 4.6/5 (100+ reviews)

Grading and assessment, traditionally time-consuming and often subjective, have been given a 21st-century facelift with the introduction of Gradescope. This AI-enhanced platform has been specifically designed to streamline the grading process for instructors and provide valuable feedback for students.

With the detailed rubrics used in Gradescope, students clearly understand how they’re assessed, minimizing subjectivity and promoting fairness. Since instructors can grade similar answers in batches, students are ensured consistent feedback, even in large classes.

The efficiency of Gradescope means that instructors can grade assignments faster, leading to quicker feedback for students. The direct annotations on assignments allow students to see exactly where they excelled or where they need improvement, facilitating better understanding and growth.

Gradescope, with its blend of AI enhancement and user-centric design, is transforming the landscape of academic assessments. For students, it’s not just about receiving grades but gaining a clearer, more transparent insight into their academic progress and areas of growth.

Gradescope best features

• Gradescope allows instructors to create detailed rubrics, ensuring that grading criteria are consistent and transparent. Once a rubric is set for a particular answer, it can be applied to similar answers, speeding up the process
• The platform provides an easy-to-use interface where assignments can be scanned and uploaded. It supports various formats, making it versatile for different types of assessments
• Instructors can provide specific feedback and annotations directly on the submitted work
• Gradescope can analyze assignments to detect potential similarities with other submissions, helping uphold academic integrity
• Gradescope can integrate seamlessly with popular LMS platforms, ensuring that grades and feedback are easily accessible to students

Gradescope limitations

• For educators unfamiliar with the platform, setting up assignments and rubrics on Gradescope can take some time initially. It requires understanding the platform’s unique grading methodology and interface
• If students’ written answers (for scanned assignments) are not clear or legible, the platform can struggle to identify and categorize them correctly, which can sometimes affect the grading process
• While Gradescope’s AI-assisted grading is revolutionary, it works best for specific question types. More subjective or open-ended responses might not benefit as much from the batch grading feature
• While Gradescope aims to integrate with many Learning Management Systems, occasional syncing issues or discrepancies might arise, requiring manual intervention

Gradescope pricing

• Basic: $1/month per user
• Team: $3/month per user
• Solo: $3/month per user

Gradescope ratings and reviews

• G2: 4.1/5 (6+ reviews)
• Capterra: 4.7/5 (3+ reviews)

Check out these AI calendar tools !

In today’s fast-paced academic world, where lectures, seminars, and group discussions are the norm, having a tool to capture, transcribe, and analyze spoken content can be invaluable. Enter Otter.ai, a cutting-edge AI-powered transcription service that’s been a game-changer for countless students. 

By converting speech to text in real-time, Otter.ai doesn’t just transcribe; it transforms how students interact with auditory content. With Otter.ai, students can capture every word of a lecture, ensuring that no important detail is missed. Without the pressure of note-taking, students can be more present during lectures, focusing on understanding and internalizing content.

Transcriptions can be a valuable study aid, helping students review and revise their course content more effectively. For students with disabilities or non-native speakers, having a written transcript can immensely benefit comprehension.

Otter.ai stands out as a stellar AI tool, perfectly poised to meet the multifaceted needs of students. Whether revisiting complex lecture topics, collaborating on group projects, or ensuring that no spoken word gets missed, Otter.ai is a student’s trusty companion in the academic journey.

Otter.ai best features

• Otter.ai can transcribe lectures, meetings, and conversations in real time, allowing students to focus on listening and engaging rather than frantic note-taking
• Even in group settings, the platform can identify and differentiate between various speakers, ensuring that transcriptions are clear and organized
• Transcriptions are easily searchable, allowing students to quickly locate specific topics, phrases, or sections of a lecture
• Otter.ai can integrate with various platforms, like Zoom, to directly transcribe online lectures and meetings
• The tool allows users to add custom vocabulary, ensuring that industry or subject-specific jargon is transcribed accurately
• Transcriptions are securely stored in the cloud, ensuring that they’re easily accessible from any device
• Students can effortlessly share their transcriptions with peers, making collaborative study sessions or group projects more efficient

Otter.ai limitations

• Even though Otter.ai is one of the best in its field, no transcription service is flawless. Mispronunciations, heavy accents, or background noise can occasionally lead to transcription errors
• For real-time transcription, a stable internet connection is crucial. A weak or fluctuating connection could disrupt the service
• While the free version is useful, it comes with a monthly transcription limit, which might be restrictive for students with heavy usage

Otter.ai pricing

• Basic : Free
• Pro : $10/month per user
• Business : $20/month per user
• Enterprise : Contact Otter.ai for pricing

Otter.ai ratings and reviews

• G2: 4.0/5 (100+ reviews)
• Capterra: 4.5/5 (60+ reviews)

In the domain of language learning and vocabulary enhancement, Knowji stands out as a shining star. This AI-driven app combines the strengths of cognitive science, pedagogical principles, and cutting-edge technology to offer a unique learning experience. 

Tailored specifically for students, Knowji seeks to transform the often daunting task of vocabulary building into an engaging and productive endeavor. Through visual mnemonics and spaced repetition, Knowji ensures that vocabulary is learned and retained for the long term.

The app’s interactive interface and rich visual and auditory content make vocabulary learning more engaging and less tedious. The AI-driven adaptability ensures that students aren’t overwhelmed or under-challenged, making their learning journey more efficient and rewarding.

With contextual sentences, students gain a deeper understanding of how each word fits into everyday language.

Knowji isn’t just another vocabulary app; it’s a holistic learning ecosystem. With its fusion of AI technology, cognitive science principles, and pedagogical insights, Knowji positions itself as an indispensable tool for students aiming to expand their linguistic horizons.

Knowji best features

• The audio features instill confidence in students, ensuring they can pronounce new words correctly
• The student progress tracking features allow students to set and achieve vocabulary goals, giving them a clear sense of direction and accomplishment
• Based on individual student progress and performance, Knowji’s AI algorithms adapt to provide learners with tailored content, ensuring they are always challenged at the right level
• To provide context, words are paired with example sentences, helping students understand their practical application
• Knowji uses the principles of spaced repetition, presenting words at optimal intervals to ensure long-term retention

Knowji limitations

• Knowji’s vocabulary lists are curated for certain age groups and exam preparations. Some users might find the need for more advanced or diverse word lists, especially for specialized academic or professional usage
• The app heavily relies on visual mnemonics and auditory cues. Students who don’t resonate with these learning styles might find other methods more effective
• The rich visual and auditory content, while beneficial for learning, might consume a significant amount of device memory, especially if multiple-word lists are downloaded
• No desktop version

Knowji pricing

• Varies by module. Visit the Apple Store or Google Play Store for pricing

Knowji ratings and reviews

• Capterra: N/A

In the bustling world of artificial intelligence, OpenAI emerges as one of the industry’s foremost leaders. With its commitment to ensuring that artificial general intelligence (AGI) benefits all of humanity, OpenAI has released a suite of tools and platforms with immense potential for academic arenas. 

OpenAI’s offerings can be revolutionary for students, ushering in a new era of research, understanding, and knowledge dissemination. OpenAI’s extensive library of research papers and studies serves as a valuable reservoir of knowledge for students.

Language models like GPT can assist in drafting, editing, and even brainstorming, enhancing students’ writing and research capabilities.

OpenAI isn’t just a name in the AI industry; it’s a beacon of student progress, innovation, and responsible growth. For students, it presents a golden opportunity to be part of the AI revolution, ensuring they’re equipped, enlightened, and empowered for the challenges and opportunities of tomorrow.

OpenAI best features

• Natural language processing makes it easy for students to get answers simply by typing in a question
• Students can use Dall-E to create artwork for their presentations
• OpenAI can adjust its tone, language, and sentence structure to fit the level of understanding a student has of the subject

OpenAI limitations

• Even though OpenAI emphasizes ethical AI, students need to be cautious and educated about the potential misuse of such powerful tools, especially in academic settings, to prevent plagiarism or misrepresentation
• Some of OpenAI’s advanced models, like the larger versions of GPT, demand significant computational resources for training, which might be out of reach for the average student

OpenAI pricing

• Depends on the model used and a number of words produced. Visit OpenAI for pricing

OpenAI ratings and reviews

• G2: 4.7/5 (300+ reviews)
• Capterra: 4.4/5 (20+ reviews)

Navigating the digital age, students consistently search for tools to streamline their learning process and enhance productivity. Enter Audiopen.ai—a groundbreaking AI solution that magically transforms voice notes into refined, publish-ready text. Whether you’re a student drafting a research paper, pondering over a challenging essay topic, or simply brainstorming ideas, Audiopen.ai is here to redefine your content creation experience. 

Using Audiopen.ai, you can draft papers, memos, and emails in a fraction of the usual time, enhancing productivity. The tool makes it easy to navigate from vague ideas to coherent, publish-ready text effortlessly.

The tool’s adaptability to individual writing styles ensures the output reflects your authentic voice. Whether you’re verbalizing an email, text, or a blog post, Audiopen.ai is your one-stop solution.

Audiopen.ai best features

• With tagging, your notes are always accessible and well-organized
• The multilingual feature ensures non-native English speakers can equally benefit
• Add in your specific vocabulary—perfect for proper nouns or academic terms
• Whether you’re going for a casual email vibe or aiming for crystal clear precision, Audiopen.ai can adapt its writing style. There’s even an option for a customized style that mirrors your unique voice
• The AI is designed to weed out filler words, repetitive phrases, and any incoherent segments, giving you concise and meaningful content
• Web and mobile app availability ensures easy access from any device, anytime
• It comes with a handy AI Chrome extension

Audiopen.ai limitations

• The transcription time for the free version can feel limiting
• This is a very new app, so some bugs remain. However, the developer is responsive to feature requests and concerns

Audiopen.ai pricing

• Price: $75/year per user

Audiopen.ai ratings and reviews

Brainly is kind of like academic Reddit. Powered by students, experts, and academics around the globe, its database now boasts more than 250 million answers to every question under the sun.

Developed in collaboration with OpenAI’s GPT-4 technology, Brainly’s latest AI capabilities employ its vast knowledge base to furnish a more vibrant, tailored, and efficient learning journey.

Brainly’s enhanced features make AI-powered learning tools conveniently accessible, empowering students to seek homework assistance, enrich their subject comprehension, and bridge classroom knowledge gaps.

Brainly’s mission is clear: to bolster understanding and accelerate learning in this dynamic digital age.

Brainly best features

• Learners can now opt for a “Simplify” function for straightforward explanations or “Expand” for a more thorough breakdown of topics. This allows students to customize the depth of their learning based on their individual needs
• Students can now ask follow-up questions or request detailed explanations on previous responses
• To ensure the reliability of information, Brainly incorporates expert moderators who oversee content quality
• Beyond just finding answers, Brainly provides a platform for students to discuss, debate, and delve deeper into topics with peers from around the world
• To encourage participation and consistent learning, Brainly has incorporated gamification elements like points and ranks
• Brainly’s search functionality uses AI to deliver the most relevant answers, making the quest for information efficient

Brainly limitations

• Since a significant portion of Brainly’s content is user-generated, there can be occasional discrepancies in the quality and accuracy of answers. While the platform does employ moderation, the vast number of contributions can lead to some incorrect or suboptimal answers slipping through
• Even though Brainly operates in multiple languages and regions, the quality of content can sometimes vary across these languages, leading to discrepancies in the information available to students from different countries
• Some of Brainly’s premium features are behind a paywall, which might not be accessible to all students

Brainly pricing

• Plus: $24/year per user

Brainly ratings and reviews

• G2: 4.0/5 (13+ reviews)
• Capterra: 4.6/5 (20+ reviews)

Rooted in the mission of crafting unparalleled digital learning experiences, Smart Sparrow specializes in adaptive, simulative, and gamified learning environments. They are your partners in bringing visions to life, offering services from strategic consulting to custom software development.

Smart Sparrow uniquely marries the power of AI with the elegance of design.The editable templates and an extensive component library ensure that designing visually-rich, interactive courseware is a breeze.

With granular user permissions, collaborate on courseware creation with peers, colleagues, and external vendors.

Whether you deploy through your preferred Learning Management System or use Smart Sparrow’s platform, there’s flexibility at every step. Plus, with gradebook sync, keeping track becomes easier.

Smart Sparrow isn’t just another eLearning platform; it’s a movement towards more personalized, engaging, and innovative education technology. With its myriad features and a strong emphasis on user experience, it truly embodies the future of digital learning.

Smart Sparrow’s best features

• The platform boasts a WYSIWYG (What You See Is What You Get) authoring tool, allowing educators and students to create stunning and impactful eLearning experiences effortlessly
• With rich text editing, high-fidelity media import, and custom CSS, the potential for personalization is boundless
• The built-in Analytics and reports go beyond mere grades, offering deep insights into student learning patterns, pinpointing problem areas, and understanding how students navigate and interact with content
• From dragging and dropping elements, choosing from a vast array of interactive components, and customizing lesson plans, Smart Sparrow ensures a seamless digital journey
• Create personalized lesson plans that students love. Import rich simulations, tasks, and activities that propel students to lean in and engage actively

Smart Sparrow limitations

• The vast array of features and customization options can be initially overwhelming for users unfamiliar with eLearning authoring tools. It might take some time for educators, especially those less tech-savvy, to get comfortable navigating and maximizing the platform’s potential
• Although Smart Sparrow boasts LMS integration capabilities, users may face occasional hiccups or compatibility issues when syncing with certain Learning Management Systems
• Depending on the institution’s budget, the range of features and advanced capabilities might come at a price point that could be challenging for smaller institutions or individual educators
• While the platform is mobile and tablet-ready, the experience on these devices might not always be as seamless or intuitive as on a desktop, especially when accessing more complex simulations or activities

Smart Sparrow pricing

• Up to 5 learners: Free
• Up to 100 learners: $15/user per course
• Up to 500 learners: $12/user per course
• 500+ learners: Contact Smart Sparrow for pricing

Smart Sparrow ratings and reviews

The education landscape has experienced a paradigm shift with the advent of digital tools. Amidst a plethora of online resources, Wolfram Alpha stands out as an unparalleled computational knowledge engine. 

Designed to serve both students and professionals, it goes beyond simple search to offer answers to complex questions across multiple disciplines. Wolfram Alpha’s unique approach to online search is what sets it apart. Unlike traditional search engines that pull up web pages containing possible answers, Wolfram Alpha computes answers on the fly. This means students get direct and precise answers to specific questions, ranging from mathematical equations to historical data.

Whether you’re a history buff, a budding physicist, or a math enthusiast, Wolfram Alpha has you covered. It spans mathematics, science, engineering, geography, history, and music. Instead of just offering answers, Wolfram Alpha often provides additional information and related topics, encouraging students to explore further and satisfy their curiosity.

Wolfram Alpha is more than just a search engine. It’s a student’s companion in the journey of knowledge. Its computational prowess and extensive knowledge base ensure that students are not merely searching but truly understanding.

Wolfram Alpha’s best features

• The engine understands natural language, which means students don’t need to phrase questions in a specific technical format
• With dedicated apps for both iOS and Android, this virtual learning assistant is not confined to a desktop. Whether on a bus or in a cafe, students can have the vast computational power of Wolfram Alpha right in their pocket
• Numbers and data come alive with Wolfram Alpha’s dynamic visualization capabilities. Graphs, charts, and other visual representations help students grasp complex concepts more intuitively.
• For students grappling with math problems, Wolfram Alpha doesn’t just provide the answer but can also showcase a step-by-step breakdown of the solution, aiding in understanding and learning

Wolfram Alpha limitations

• While Wolfram Alpha can handle a wide range of questions, there’s a learning curve involved in phrasing complex queries to get the desired result
• It might not be the go-to tool for subjective topics, opinion-based questions, or areas that require human judgment
• For highly specialized academic or research-based questions, the platform might sometimes provide a more generalized answer, which might not delve into the nuances a student or researcher might be looking for

Wolfram Alpha pricing

• Basic: Free
• Pro: $7.25/month per user
• Pro Premium: $12/month per user

Wolfram Alpha ratings and reviews

• G2: 4.7/5 (3+ reviews)

ClickUp: Acing The Test As The Premier AI Tool For Students

ClickUp brings to the table a suite of features specifically designed to adapt to the dynamic nature of student life. From group projects to thesis deadlines, ClickUp is the silent digital assistant every student wishes they had earlier. Its AI-driven insights help students prioritize, optimize, and visualize their academic journey, ensuring everything runs smoothly.

As we’ve navigated through various amazing AI tools that promise to revolutionize education, ClickUp stands a class apart. Not because it claims to do everything but because it delivers on its promise, ensuring students are equipped, empowered, and always ahead in their academic journey.

As the school year continues and challenges arise, students can rest easy knowing that with ClickUp, they’ve already secured an A+ in preparedness.

Questions? Comments? Visit our Help Center for support.

Receive the latest WriteClick Newsletter updates.

Thanks for subscribing to our blog!

Please enter a valid email

• Free training & 24-hour support
• Serious about security & privacy
• 99.99% uptime the last 12 months

8 Ways to Create AI-Proof Writing Prompts

C reating 100 percent AI-proof writing prompts can often be impossible but that doesn’t mean there aren’t strategies that can limit the efficacy of AI work. These techniques can also help ensure more of the writing submitted in your classroom is human-generated. 

I started seeing a big uptick in AI-generated work submitted in my classes over the last year and that has continued. As a result, I’ve gotten much better at recognizing AI work , but I’ve also gotten better at creating writing prompts that are less AI-friendly. 

Essentially, I like to use the public health Swiss cheese analogy when thinking about AI prevention: All these strategies on their own have holes but when you layer the cheese together, you create a barrier that’s hard to get through. 

The eight strategies here may not prevent students from submitting AI work, but I find these can incentivize human writing and make sure that any work submitted via AI will not really meet the requirements of the assignment. 

1. Writing AI-Proof Prompts: Put Your Prompt Into Popular AI tools such as ChatGPT, Copilot, and Bard 

Putting your writing prompt into an AI tools will give you an immediate idea of how most AI tools will handle your prompt. If the various AI chatbots do a good, or at least adequate, job immediately, it might be wise to tweak the prompt. 

One of my classes asks students to write about a prized possession. When you put this prompt into an AI chatbot, it frequently returns an essay about a family member's finely crafted watch. Obviously, I now watch out for any essays about watches. 

2. Forbid Cliché Use

Probably the quickest and easiest way to cut back on some AI use is to come down hard on cliché use in writing assignments. AI tools are essentially cliché machines, so banning these can prevent a lot of AI use. 

Equally as important, this practice will help your students become better writers. As any good writer knows, clichés should be avoided like the plague. 

3. Incorporate Recent Events

The free version of ChatGPT only has access to events up to 2022. While there are plugins to allow it to search the internet and other internet-capable AI tools, some students won’t get further than ChatGPT. 

More importantly, in my experience, all AI tools struggle to incorporate recent events as effectively as historic ones. So connecting class material and assignments to events such as a recent State of Union speech or the Academy Awards will make any AI writing use less effective. 

4. Require Quotes

AI tools can incorporate direct quotations but most are not very good at doing so. The quotes used tend to be very short and not as well-placed within essays. 

Asking an AI tool for recent quotes also can be particularly problematic for today’s robot writers. For instance, I asked Microsoft's Copilot to summarize the recent Academy Awards using quotes, and specifically asked it to quote from Oppenheimer's director Christopher Nolan’s acceptance speech. It quoted something Nolan had previously said instead. Copilot also quoted from Wes Anderson’s acceptance speech, an obvious error since Anderson wasn’t at the awards .  

5. Make Assignments Personal

Having students reflect on material in their own lives can be a good way to prevent AI writing. In-person teachers can get to know their students well enough to know when these types of personal details are fabricated. 

I teach online but still find it easier to tell when a more personalized prompt was written by AI. For example, one student submitted a paper about how much she loved skateboarding that was so non-specific it screamed AI written. Another submitted a post about a pair of sneakers that was also clearly written by a "sole-less" AI (I could tell because of the clichés and other reasons). 

6. Make Primary or Scholarly Sources Mandatory

Requiring sources that are not easily accessible on the internet can stop AI writing in its tracks. I like to have students find historic newspapers for certain assignments. The AI tools I am familiar with can’t incorporate these. 

For instance, I asked Copilot to compare coverage of the first Academy Awards in the media to the most recent awards show and to include quotes from historic newspaper coverage. The comparison was not well done and there were no quotes from historical newspaper coverage. 

AI tools also struggle to incorporate journal articles. Encouraging your students to include these types of sources ensures the work they produce is deeper than something that can be revealed by a quick Google search, which not only makes it harder for AI to write but also can raise the overall quality.  

7. Require Interviews, Field Trips, Etc. 

Building on primary and scholarly sources, you can have your students conduct interviews or go on field trips to historic sites, museums, etc. 

AI is still, thankfully, incapable of engaging in these types of behavior. This requires too much work for every assignment but it is the most effective way to truly ensure your work is human- not computer-written. 

If you’re still worried about AI use, you can even go a step further by asking your students to include photos of them with their interview subjects or from the field trips. Yes, AI art generators are getting better as well, but remember the Swiss cheese analogy? Every layer of prevention can help. 

8. Have Students Write During Class

As I said to start, none of the methods discussed are foolproof. Many ways around these safeguards already exist and there will be more ways to bypass these in the future. So if you’re really, really worried about AI use you may want to choose what I call the “nuclear option.” If you teach in person you can require students to write essays in person. 

This approach definitely works for preventing AI and is okay for short pieces, but for longer pieces, it has a lot of downsides. I would have trouble writing a long piece in this setting and imagine many students will as well. Additionally, this requirement could create an accusatory class atmosphere that is more focused on preventing AI use than actually teaching. It’s also not practical for online teaching. 

That all being said, given how common AI writing has become in education, I understand why some teachers will turn to this method. Hopefully, suggestions 1-7 will work but if AI-generated papers are still out of hand in your classroom, this is a blunt-force method that can work temporarily. 

Good luck and may your assignments be free of AI writing! 

• 7 Ways To Detect AI Writing Without Technology
• Best Free AI Detection Sites
• My Student Was Submitting AI Papers. Here's What I Did

All done here 🥳

Can we use optional cookies?

We use some essential cookies to make this website work.

We won’t turn them on unless you accept. Want to know more or adjust your preferences? Here’s our cookie notice .

Adjust your cookie preferences

We use 2 types of cookie. You can choose which cookies you are happy for us to use. For more detail, and a list of the cookies we use, see our cookie notice .

The science-y sounding cookie that is interested in what you do on our website. Where you came from, what pages you visit and for how long.

This trusty cookie is a must for our website to work and keep you safe and secure.

Mark This For Me

Your AI assignment companion tool

We are on Product Hunt

Support us 💙

Get personalised and instant feedback anytime .

Assignment feedback is limited, however that shouldn't stop you from staying motivated and unlocking new opportunities for success.

You're 2 steps away

A platform for students.

We take pride in being the go-to feedback solution for students from these schools, gaining valuable insights.

Austin Community College District

Edge Hill University

University of Birmingham

The University of Manchester

Henley Highschool

University of Exeter

Otago Polytechnic

PLC Armidale

Wiltshire University

Chelmsford College

Instant Feedback? Yes. Free? Sure 👀

An extra pair of virtual eyes just in-case.

Top questions from our FAQs

Student Question

I am scared of using AI because of plagiarism

Our tools do not give you answers. We focus only on giving guidance and feedback on what you have already written. The feedback you receive aims to give enough but not everything, for example: Hey, you did a good job introducing X but you didn't really criticaly evaluate X as required in your marking criteria.

Now imagine this example but across your entire assignment.

What happens with the assignments I provide?

Your assignments and assignment critera that you provide is processed through ChatGPT's APIs owned by OpenAI. The data given through their APIs is not used to train their models. We securely store your data on our servers until you tell us you want your data deleted. You can learn more about how your data is stored and managed by looking at our terms of use and our privacy policy.

Have a question?

Reach out to us here by emailing [email protected] or tag us on our social media.

Check out our plans

10,000 words

Free lifetime

For students needing occasional one-off feedback on assignments

Personal dashboard to view your AI-generated feedback

Support for any issues that you raise

250,000 words

£3.99 per month

For students needing frequent feedback on assignments.

Everything in Personal

Download and print your feedback for offline use

Wordback feature

Cancel at any time

Psst, Did you know?

Students on MTFM have rocked over

words from their marking criteria and assignments—getting instant personalised feedback.

Have you tried properly learning with AI yet?

Over 400 + assignments marked and feedback given without breaking a sweat.

We've helped students across the world to access personalised and instant feedback for their assignments.

The Straits Times

• International
• Print Edition
• news with benefits
• SPH Rewards
• STClassifieds
• Berita Harian
• Hardwarezone
• Shin Min Daily News
• SRX Property
• Tamil Murasu
• The Business Times
• The New Paper
• Lianhe Zaobao
• Advertise with us

Students at S’pore universities allowed to use AI tools for assignments but must stick to rules

SINGAPORE - Since 2023, students enrolled in Singapore universities have been allowed to use artificial intelligence (AI) tools to complete their assignments, but they cannot flout rules on things like academic honesty and plagiarism.

Incorporating the use of AI tools is aimed at boosting the quality of teaching and learning, and embracing technological advancements, said university lecturers and administrators The Straits Times spoke to.

However, undergraduates are required to adhere to rules and restrictions to make sure they learn to think independently and understand the course material, they added.

The Singapore Institute of Technology (SIT), for example, said on its website that students are not to use generative AI as a primary source of information. Instead, they are encouraged to use it as a tool – unless, of course, the assignment is to “critically evaluate the generative AI response”.

Generative AI refers to software or tech tools used to create content like text, images and videos based on prompts from a user. The AI tool is able to learn writing patterns and structures through a training period in which users test and use the software.

It is then able to generate new data that has similar characteristics to what it has learnt. Some examples of generative AI tools are ChatGPT and Sora.

Associate Professor Karin Avnit, who is deputy director at the SIT Teaching and Learning Academy, said the university’s approach is to take advantage of AI tools when they contribute to the learning process and experience.

She said: “We adopted this approach early last year when it became clear that generative AI has a great potential to enhance teaching and learning practices, as well as the potential to change industry practices.”

She added that different disciplines have varying needs in terms of teaching, learning and assessment, and so, “having hard rules may not serve the needs well”.

Prof Avnit said students who use AI tools to generate written work without the required analysis and other requirements of the assignment will not be awarded marks.

The other five public autonomous universities – the National University of Singapore (NUS), Nanyang Technological University (NTU), Singapore Management University (SMU), Singapore University of Social Sciences (SUSS), and Singapore University of Technology and Design (SUTD) – all adopt a similar position on the use of AI by students.

For instance, NUS, on its website, said students have to acknowledge the use of AI-generated content through a note or via the methods section at the end of an assignment, and explain “which AI tools were used, in which parts of the process they were used, what were the prompts used to generate results, and what did one do with the outputs to add value”.

NUS education and technology associate provost Melvin Yap said AI can play an important role to unlock, guide and support the development of such skills.

“It is, therefore, important that our students know how to use the AI tools effectively in their studies and in the future when they join the workforce,” he added.

However, Associate Professor Yap added that passing off content that was generated by AI as one’s own work is plagiarism and academic dishonesty, which is prohibited.

“Our students are given guidance on how to correctly acknowledge the use of AI tools in their projects and assignments,” he added.

SUTD on its website said AI tools can be used to enhance students’ learning, but it is “not a replacement for their intellectual contribution”.

It said: “Students can use generative AI tools in class, assignments, assessments, examinations... only when explicitly permitted by the instructor.”

In response to queries, SUTD spokeswoman Tammy Tan said the university “relies on both AI detection tools and instructors to identify the potential use of generative AI”.

She added that students are not given extra marks for not using AI tools, so they have little incentive to not acknowledge its use in their work.

In response to queries, an SUSS spokeswoman said the university has measures in place to ensure the ethical use of AI tools. For instance, it uses a software tool called Turnitin to detect work generated by AI technology.

She added that plagiarism policies are also in place, and if a student is found to have plagiarised schoolwork or is suspected of academic misconduct, SUSS will take steps to determine the originality of the written assignment.

An NTU spokesman, responding to queries, said: “Preventing the use of generative AI in classes will not stop students from using it.

“Hence, it is important that we equip students with the knowledge and skills to use these generative AI technologies productively in an ethical and critical manner... to help them sharpen their cognitive skills.”

In a speech on March 6, Education Minister Chan Chun Sing said: “We see AI as having great potential to disrupt.

“However, if we harness it well, and we manage it well... it will allow us to transcend our constraints of old, to ride the next S-curve of economic growth.”

He added that Singapore’s educational institutions must train a new generation of people that will enable this disruption to be harnessed and managed.

Experts said the move to embrace AI in public universities is a step in the right direction, but it must be managed carefully.

Associate Professor Jason Tan, who teaches at the National Institute of Education, said it is important for students to first understand that one key purpose of higher education is to “provide students with the opportunity to further develop higher-order thinking skills”.

Once students are aware of this, they will understand how to appropriately use AI tools in their education, he added.

Prof Tan said higher-order thinking skills include “gathering, synthesising, organising and evaluating information”, and students require “explicit guidance” for them to know how to best use AI tools.

Dr Felix Tan, who has been teaching at Singapore polytechnics and universities for more than 20 years, said AI tools can help students with framing their thoughts and ideas, but educators should examine written assignments and ensure that a fair amount of work has been put in by the student, and grade it accordingly.

He said: “I will look at whether their essays are supported by legitimate evidence and research. How are the points crafted? Is it well-structured? Did it use the theories that were discussed in class, and how they are applied?

“A good essay should have a voice and an opinion of sorts. It should remain personable but also be backed by academic resources.”

Social sciences undergraduate Geneve Tay, 21, who declined to name the university she attends, said she welcomed the move to allow the use of AI tools for written assignments, and that she has occasionally used such tools in her schoolwork.

She said: “Being allowed to use such tools shows we are progressive and keeping up with technological advancement.

“However, I do not use generative AI often because it requires a lot of work, like tweaking the content it produces and editing it to suit the assignment objectives. Sometimes, it may take even more effort than doing the entire assignment myself.”

Clerical assistant Sujatha Maniam, 53, whose 24-year-old son is a final-year student at NUS, said she was at first concerned when her son said he could use AI tools for schoolwork.

She said: “What’s the point if a computer is going to do all his work for him? Will he learn?”

However, her fears were dispelled when he assured her that he still has to use his own words and not use wholesale whatever is AI-generated, she added.

Join ST's WhatsApp Channel and get the latest news and must-reads.

• Higher education
• Education and schools
• Universities - Singapore
• AI/artificial intelligence

Read 3 articles and stand to win rewards

Spin the wheel now

Detecting AI-Generated Code Assignments Using Perplexity of Large Language Models

• Zhenyu Xu Texas Tech University
• Victor S. Sheng Texas Tech University

• Video/Poster

How to Cite

• Endnote/Zotero/Mendeley (RIS)

Information

• For Readers
• For Authors
• For Librarians

Developed By

Subscription.

Login to access subscriber-only resources.

Part of the PKP Publishing Services Network

Copyright © 2024, Association for the Advancement of Artificial Intelligence

Classroom Q&A

With larry ferlazzo.

In this EdWeek blog, an experiment in knowledge-gathering, Ferlazzo will address readers’ questions on classroom management, ELL instruction, lesson planning, and other issues facing teachers. Send your questions to [email protected]. Read more from this blog.

How to Use AI Tools to Support English-Language Learners

• Share article

I have shared many columns about how teachers might want to consider—and how they might not want to consider—using artificial intelligence in the classroom.

You can see many of those previous posts here . You can also see many more ed.-related resources here , including two animated videos about AI in education that Katie Hull and I did with Education Week.

Today’s post focuses on using artificial intelligence with English-language learners (as did a previous one ).

Few teachers have had more experience applying AI tools with ELLs than Svetlana Kandybovich, and she agreed to contribute to today’s post. Svetlana includes links to free AI tools she has created for teachers to use with students.

Opportunity or Remix?

Svetlana Kandybovich is a teacher, teacher trainer, and materials writer with more than 20 years of international ELT (English-Language Teaching ) experience. She shares her insights on teaching, learning, and professional development with fellow educators and teacher trainers through her blog, ELTcation .

Do GenAI-powered tools offer new opportunities for language teaching and learning, or are they simply old school concepts remixed with AI technology?

The ease of creating GenAI-powered tools has led to an “AI rush” among edupreneurs, offering various tools promising to revolutionize language learning by making it more engaging, personalized, adaptive, and inclusive. However, as with any other new or emerging technology, without proper integration into our practices to ensure it truly adds value to learning, this potentially powerful technology might just end up being wasted.

What Makes GenAI Effective?

A tool is effective when it adds value to learning. Following the SAMR approach , the impact of a new tool is higher when it transforms learning by redesigning or redefining the pedagogy and introduces new possibilities that were previously unimaginable. Put simply, a tool is most valuable when it is indispensable and helps teachers create a better learning environment than any other methods or tools available.

When used effectively, every tool has the potential to improve learning and learning outcomes, but it’s the teacher’s consistent and principled approach that truly makes it work.

Image by Svetlana Kandybovich

Key Elements

When it comes to effectively using and integrating GenAI, three things are key: the teacher’s expertise, understanding GenAI, and being creative. They are all tied to how GenAI works, which can be likened to a game of chance. While we can manage the input, no one has complete control over what comes out of GenAI (and likewise, nobody has fully understood its capabilities yet). This highlights the importance of teachers being experts in their field .

To achieve quality results, teachers should have a clear idea of their desired output and the ability to evaluate, iterate, and fine-tune it further. Teachers’ AI literacy is essential for addressing the limitations and risks associated with GenAI, while creativity is needed to push boundaries, explore new activities and tasks, and unlock the technology’s potential to make learning even better.

GenAI Use Cases

We can discern quite distinct ways in which language teachers use GenAI by studying their experiences shared in blog posts, social media groups, forums, and during webinars and conferences.

The largest group by far involves replicating and automating existing practices. Many examples of this can be found, ranging from direct use of large language models (LLMs) or single solutions and apps like ChatGPT , Copilot , or Gemini , to various platforms built on top of LLMs designed for educators of various subjects, such as MagicSchool or RockettAI , and for language teachers in particular, such as Twee or LingoTeach . These platforms enable teachers to create a wide range of worksheets, develop lesson plans, write texts on any topic and for any proficiency level, and design various types of exercises . They leverage the capabilities of LLMs, particularly their superfast text generation. The idea is to save time, but speed isn’t everything.

Sometimes, just like with any other third-party tool, your pedagogical approach may differ from that of platform developers. Therefore, what these platforms churn out might not fit your needs perfectly. Without the right customization options, they might only provide a quick solution that doesn’t truly benefit your learners, leaving you needing to invest more time to fix things up.

Text modification and the creation of multimodal resources are two of the areas where GenAI can provide invaluable support for language teachers. For instance, with tools like Elevenlabs for generating synthetic voices, and a range of image-, animation-, and video-generation tools such as Dalle-3 , Adobe Express , D-ID or ArtFlow , we can create diverse multimodal materials and activities. Achieving this without such technology would be extremely challenging, if not impossible.

The impact level increases when tools are customized to meet specific needs and provide teachers with customization functionality, allowing them to incorporate their unique contexts and experiences. For instance, I have developed two tools to aid language teachers in brainstorming and designing personalized activities for their learners.

The Five-Minute Activity Generator helps language teachers come up with quick activities for the classroom, while the Role-Play Generator is crafted to generate role-play scenarios and role-play cards tailored to learners’ needs and learning objectives. Both tools tap into the content-generation powers of LLMs and are great for sparking ideas. But what really makes the magic happen is when teachers put their own twist on things, adding their personal touch and context details.

One novel use case involves the creation of AI-powered chatbots using various GenAI tools to simulate real-life interactions and offer new learning experiences. These chatbots can be designed as both stand-alone activities and as part of specific lessons. You can assign a particular persona to a chatbot, whether it’s an imaginary character or a famous person, and it will act accordingly. For example, in the Tumbleweed Invasion lesson , learners engage in dialogue with Alex the chatbot to uncover the story’s details as narrated by Alex.

I have created and tested several chatbots to support my learners, each with different objectives that define their behavior and language. For instance, I’ve developed ThinkChat Buddy to assist my intermediate and upper-intermediate learners in practicing conversation skills across various scenarios. Essentially, it acts as a conversation scaffold, guiding learners through dialogues by thinking out loud, explaining why it responds as it does, clarifying expectations, and providing gentle and encouraging feedback. This chatbot is not a replacement for classroom conversation practice; it’s a supportive tool that extends learners’ practice, preparing them for real-life conversations.

Two important elements of using chatbots effectively in language learning are their design and monitoring. To prevent chatbots from becoming just one-time engagement tools, it’s essential to align their behavior, language, and instructions with learners’ specific needs, proficiency levels, and learning objectives . From my observations, even proficient learners often struggle with unfocused chatbot interactions, when they are simply instructed to “go and chat,” resulting in minimal learning value. Additionally, circling back to the issue of control over GenAI output and its associated risks, it’s essential for teachers to closely monitor learner-chatbot interactions and quickly adjust chatbot tasks and behaviors as needed.

As GenAI continues to advance, we will discover even more new ways it can enhance and transform language learning. Yet, its effectiveness truly depends on the skill level of the teachers, their understanding of AI, and their ability to think creatively.

Consider contributing a question to be answered in a future post. You can send one to me at [email protected] . When you send it in, let me know if I can use your real name if it’s selected or if you’d prefer remaining anonymous and have a pseudonym in mind.

You can also contact me on Twitter at @Larryferlazzo .

Just a reminder; you can subscribe and receive updates from this blog via email . And if you missed any of the highlights from the first 12 years of this blog, you can see a categorized list here .

The opinions expressed in Classroom Q&A With Larry Ferlazzo are strictly those of the author(s) and do not reflect the opinions or endorsement of Editorial Projects in Education, or any of its publications.

Sign Up for EdWeek Update

Edweek top school jobs.

Sign Up & Sign In

• Newsletters

IE 11 Not Supported

Report finds genai use up, plagiarism down in 7 countries, a 13-month study from copyleaks found an encouraging decline in plagiarism, and most papers and assignments completed by high school and college students were not found to contain ai-generated text..

• United States — 17 percent (AI-generated content) and 30 percent (plagiarism)
• Canada — 16 percent and 27 percent
• United Kingdom — 10 percent and 33 percent
• South Africa — 26 percent and 13 percent
• Myanmar — 23 percent and 24 percent
• Philippines — 19 percent and 30 percent
• Australia — 31 percent and 19 percent