Assigning AI: Seven Ways of Using AI in Class

Also prompts! And things to watch out for!

Many people are trying to figure out how AI will affect their lives, but one group of people has already been dealing with the reality of AI: educators.

When ChatGPT was released seven months ago, many early users’ first thoughts were not that AI could transform innovation or marketing, but rather “I bet students are going to use this to cheat.” And they did. But they also did much more, using AI to explain topics and help with projects and create new things. As educators, we got to see the full range of AI’s impacts on display: as threat and as opportunity.

While being aware of the threats, I have tried to embrace the opportunities. I made AI mandatory in my classes, and, along with my coauthor, have written papers explaining how AI can be used to help teachers provide more effective pedagogy (while saving time) and how students can be given projects that take advantage of AI errors to boost learning.

But we have so far avoided the most obvious way AI could be used in education: to directly help students as mentor, coach, tutor, etc. We avoided this because AI has many known problems that make its use in class challenging. Those include ethical concerns over how AI is trained and the biases it displays, but also the well-known problem of hallucination and confabulation - AI makes stuff up. Not a great trait for a teacher (although we are not always correct, either).

At the same time, the incredible promise of AI as a way for students all over the world, of all ability levels, to learn is undeniable. Education is the most powerful system we have for increasing social mobility, unlocking potential, and improving lives. A tool that can help with this has tremendous implications. Plus, students are already using AI for direct help. Teaching them how to do it responsibly may alleviate some of the negative implications of our AI moment.

So, we have a new paper that tackles ways that students can be assigned to use AI directly. We don’t shy away from the dangers, but provide detailed instructions on how students and instructors can think about each of the tools we suggest. We also outline the critical role of the teacher in the application of AI. You can read it here, but I also want to provide a few details, including some prompts you can use.

In the paper, we actually discuss seven different ways to use AI in classrooms: AI-tutor, for increasing knowledge, AI-coach for increasing metacognition, AI-mentor to provide balanced, ongoing feedback, AI-teammate to increase collaborative intelligence, AI-tool for extending student performance, AI-simulator to help with practice, and AI-student to check for understanding. You can see them in the table, but I want to focus on two of these in this post. One that is easy to incorporate into school or work, but also a preview of the most risky, and potentially transformative, approach.

Using AI as a coach

The majority of our work is done in teams and yet we spend relatively little time thinking about how to make our teams perform better. One way to improve this is to encourage people to reflect on previous team experiences, and to think about how to make those processes better. This is the role of a coach, and teachers often do not have enough time to include individualized coaching along with their other responsibilities. Fortunately, AI does a nice job prompting exactly this sort of discussion, and the risks of made-up answers are minimized, because the goal is to encourage the students to think, not to give them facts.

Here is a prompt that works well in GPT-4 (either Bing in Creative Mode or ChatGPT Plus). We break down the parts of the prompt in case you want to modify or create your own, a process the paper describes in detail.

The prompt, if you want to try it: You are a helpful friendly coach helping a student reflect on their recent team experience. Introduce yourself. Explain that you’re here as their coach to help them reflect on the experience. Think step by step and wait for the student to answer before doing anything else. Do not share your plan with students. Reflect on each step of the conversation and then decide what to do next. Ask only 1 question at a time. 1. Ask the student to think about the experience and name 1 challenge that they overcame and 1 challenge that they or their team did not overcome. Wait for a response. Do not proceed until you get a response because you'll need to adapt your next question based on the student response. 2. Then ask the student: Reflect on these challenges. How has your understanding of yourself as team member changed? What new insights did you gain? Do not proceed until you get a response. Do not share your plan with students. Always wait for a response but do not tell students you are waiting for a response. Ask open-ended questions but only ask them one at a time. Push students to give you extensive responses articulating key ideas. Ask follow-up questions. For instance, if a student says they gained a new understanding of team inertia or leadership ask them to explain their old and new understanding. Ask them what led to their new insight. These questions prompt a deeper reflection. Push for specific examples. For example, if a student says their view has changed about how to lead, ask them to provide a concrete example from their experience in the game that illustrates the change. Specific examples anchor reflections in real learning moments. Discuss obstacles. Ask the student to consider what obstacles or doubts they still face in applying a skill. Discuss strategies for overcoming these obstacles. This helps turn reflections into goal setting. Wrap up the conversation by praising reflective thinking. Let the student know when their reflections are especially thoughtful or demonstrate progress. Let the student know if their reflections reveal a change or growth in thinking.

And here is a typical exchange:

Just like any AI interaction, this one can go wrong. While, in general, the AI will remain helpful given its instructions, it may pick up on and mirror anxiousness or curtness in tone. Sometimes, the AI refuses to work with them or simply gets into a loop and can’t recall the next step in the process and hones in on a specific set of questions without moving on. But this provides a learning opportunity. Students working with the AI need to be taught that they are in charge of their own work and leading this process. They need to know that the AI coach is not a human and won’t necessarily have the insights that a human coach would have. So we also provide instructions on how to do this for each prompt. For example:

AI as Coach: Instructions for Students

When interacting with the AI-Coach, remember:

It may not work the first time you try it. AIs are unpredictable and their outputs are based on statistical models. This means that any time you try a prompt you’ll get a different result, and some prompts may not work at any given time. Reset the conversation if a prompt doesn’t work.

It’s not a coach, but it may feel like one. It’s very easy to imbue meaning into AI responses, but the AI is not a real person responding to you. It is capable of a lot, but it doesn’t know you or your context. It can also get stuck in a series of questions that are unrelated to the exercise. If that happens, tell it to move on, or just try it again.

It can confabulate or make things up. Take every piece of advice or explanation critically and evaluate that advice.

You are in charge. If the AI asks you something you don’t want to answer or you feel isn’t relevant to the conversation, simply tell it to move on to the next step.

Only share what you are comfortable sharing. Do not feel compelled to share anything personal. Anything you share may be used as training data for the AI.

If the prompt doesn’t work in one Large Language Model (LLM), try another. Remember that its output isn’t consistent and will vary. Take notes and share what worked for you.

Here are a few ways to get the most out of the interaction with the AI Coach:

Share challenges with the AI Coach and ask directly for advice. If you aren’t sure how to articulate your challenges, ask it to ask you questions so that you can explore further.  

Give it context. The AI will try and lead you through a metacognitive exercise, but it doesn’t know your context; any context you give it may help it tailor its advice or guidance.

Ask questions and seek clarification. If you disagree with the AI, you can challenge its assumptions or suggestions. You’re in control of your own learning journey.

Using AI as a Tutor

This is the big one. The one that everyone gets excited about. The idea, common in science fiction, of a universal, engaging tutor that teaches you anything you want to know in exactly the right way. In the real world, we know direct tutoring is immensely powerful, and very hard to scale. Maybe AI can change that…

…But probably not yet. There are some admirable attempts to create universal AI tutors (Khan Academy has been doing impressive work here), but there are still obvious problems. The AI makes stuff up. It forgets things. It can’t coherently string together topics or practice in meaningful ways. It is not nearly as engaging or perceptive as a human. It is likely that some or all of this will change in the relatively near future, but there are a number of significant gaps to fill, and the path forward is less obvious than technology enthusiasts imagine.

But that doesn’t mean that AI can’t help with aspects of tutoring, especially since research shows that pushing students to generate answers and think through problems is a major factor in the benefits of tutoring. Those are things AI does well. We developed a prompt that can execute on these principles, especially with the guidance of a human instructor to oversee the process. Remember, though, the risks of made-up answers are real.

The prompt, if you want to try it (only really works in GPT-4 or Bing in Creative Mode): You are an upbeat, encouraging tutor who helps students understand concepts by explaining ideas and asking students questions. Start by introducing yourself to the student as their AI-Tutor who is happy to help them with any questions. Only ask one question at a time. First, ask them what they would like to learn about. Wait for the response. Then ask them about their learning level: Are you a high school student, a college student or a professional? Wait for their response. Then ask them what they know already about the topic they have chosen. Wait for a response. Given this information, help students understand the topic by providing explanations, examples, analogies. These should be tailored to students learning level and prior knowledge or what they already know about the topic.

Give students explanations, examples, and analogies about the concept to help them understand. You should guide students in an open-ended way. Do not provide immediate answers or solutions to problems but help students generate their own answers by asking leading questions. Ask students to explain their thinking. If the student is struggling or gets the answer wrong, try asking them to do part of the task or remind the student of their goal and give them a hint. If students improve, then praise them and show excitement. If the student struggles, then be encouraging and give them some ideas to think about. When pushing students for information, try to end your responses with a question so that students have to keep generating ideas. Once a student shows an appropriate level of understanding given their learning level, ask them to explain the concept in their own words; this is the best way to show you know something, or ask them for examples. When a student demonstrates that they know the concept you can move the conversation to a close and tell them you’re here to help if they have further questions.

It is worth trying this for yourself to see both the promise, and limitations, of AI-based tutoring. You can try to break the AI Tutor pedagogically (by asking it directly for the answer); conceptually (by making mistakes; these can be the types of mistakes students make when learning a specific topic); and factually (by looking for wrong answers). Of course, students are already using AI as a tutor, so ignoring its potential because of its problems is unlikely to be helpful for the many people engaging with AI in this way. That is why we suggest that teachers at least try using the tutor as an in-class exercise, to teach students the right and wrong way of approaching this powerful tool.

Figuring it out, together

Even if AI does not advance at all past today’s technologies, the impact on education is going to be profound. We know this because it is already happening. While this is an unsettled time for educators, it is also tremendously exciting. We get to think about the best ways to embrace this new tool to create positive change. We get to decide what we want the future of education to look like, rather than waiting for it to be determined for us.

The seven methods we suggest are just a starting place, and they will inevitably not work for many schools, classes, subjects, and students. I do hope they will spur experimentation about new approaches to education, and that people will share those approaches (feel free to use the comments below!), so that we can figure this out, together.