Workshop
- You can find more resources (including slides and citations for this workshop) here.
- Open a few different AI models here.
- Basic Prompting: Prompting is Writing
- Search the web for innovative ways excellent faculty have taught topic/subject A. Examine best practices and the most recent literature on pedagogy and student learning. Respond as an experienced and caring professor at the university of B. Provide 10 innovative ideas for how to introduce college students in year C to topic D in class E using examples or analogies they will find relevant.
- Ask me a series of 3 or 4 questions to then make recommendations about 10 obscure composers/experiments/research ideas/restaurants/articles/books/jobs/policies [PICK ONE] I should know about. Based upon my interests and taste, make 10 well-researched recommendations for things I will enjoy (or might challenge my thinking) and include working links to sources.
- Investigate the most burning interests of students at university X in 2026. Create five excellent debate propositions that will equally divide a room of these students studying topic Y. The topics should utilize and require content knowledge of Z.
- You can find more prompt ideas under Basic Prompting.
- Searching for Ideas: Massive Contextual Search
- Find something similar to X
- What are the trends in thinking about Y in the last …
- Is there anything that I [your name] have posted in the last 10 years on social media that is overly political and might have a negative impact if I was looking for a job? Do an exhaustive search and tell me if there are any red flags in my background.
- Search for everything I need to know to prepare for an excellent job interview for position A at B and prepare a briefing document with talking points.
- You can find more of these under Searching and Reasoning.
- Agents & Research
- There is a list of agents (and more info) on the Orchestration and Agents page and how to build a skill.
- There is more (including both Deep Research Templates) on the Agentic AI Research Workflow page.
- Ask an AI to do a deep analytical dive in your field. You can either (1) copy, paste & modify the templates below, (2) modify one of the extended prompts on the Deep Research Page, or (3) ask a (good model) AI to write a prompt for you (Write an excellent prompt that will direct an AI to do X.) Select the best thinking model available and look for “Deep Research” buttons (in Gemini or ChatGPT, for example).
- Deep Research Template 1
- Create a research report that will illuminate/examine/explore X. Make sure to examine the questions A, B, and C and include an analysis of D & E. You should begin with a critical review of literature/practice/web and then provide a synthesis of the key ideas/controversies/concepts/case studies and a recommendation.
- Sources & Scope: The research should
- Draw from fields F & G,
- Methodology H
- Focus on peer-reviewed journal articles/best practices/reputable studies/institutional sources.
- Look for sector/Western/political/educational/gender bias in sources
- Seek global sources in language/culture I.
- Purpose & Framework:
- Use K as a framework for understanding these issues.
- Focus on real-world applications and capabilities.
- Pay special attention to policy implications and government uses.
- Note any potential for L.
- Audience
- Write for an audience of M/for journal N or submission to conference O.
- Describe your findings with relevance to P.
- You can find examples under Deep Research.
- Analyze Responses
- First create a Google Form survey like an exit ticket or biggest question. (AI can help with this). If you are a paid Gemini/Google user (or a Google campus) you will see a Gemini logo when you click responses and Gemini will automatically analyze and summarize your responses. Otherwise, try this prompt:
- PROMPT: Analyze these responses to a survey about X. [It often works better to do one or more of these as a follow-up.] Briefly, what are the top five themes? What is notable in its absence? What should I know as I prepare a follow-up with this group? What is the greatest problem or confusion? How can I improve?
- System Prompts samples and templates are here.
- More on Vibe Coding here.
- AI Tools are listed here.
- Emotionally expressive AI.
- Focus Groups and Empathy Interviews
- I am trying to gain a richer understanding of why students might be struggling with problem X. You will help by responding as an honest first-year/first gen/minority/non-major student to help deepen my knowledge. Question my assumptions when necessary and tell me stories to build my empathy for the real causes of this problem.
- You can find examples under Simulations, Games and Roleplaying.
IMPROVING TEACHING & DESIGN
- Test An Academic Integrity Policy
- Find the best research about the hidden curriculum for first-generation students and think about the best practices for clear communication. Then examine this policy for academic honesty and tell me what might be confusing or unclear to first-generation or under-represented students at University X about cheating. Do not summarize the research but instead, provide brief research-based guidance for how I could improve this policy and make it clearer, better and more inclusive. Create a well-designed and clear one-page infographic using our university icons and color (find the University style guide if possible) and provide me with an easy to understand, innovative and beautiful poster that would help my students follow this policy. [Insert policy or a link to website]
- There is much more research needed on what AI is doing to education, but here is a current list of the best research (over 100 peer-reviewed and published studies) and some idea for ReDesigning Learning in the Age of AI: Research and Principles.
- AI, however is a useful collaborator, precisely because it can offer advice different from our own. (Note that a System Prompt that ask explicitly to offer other opinions and to watch for our bias makes a difference.)
- Here is a basic updating prompt (that you should really use as a Skill. The procedure for that is on the Skills page.)
- REVISE the dates in this syllabus to align with the new semester, assuming I teach MWF [or TTH etc] starting on DATE.
- CHECK to make sure this syllabus complies with all university policies and required statements (religious observance, accommodations, grade dispute etc.)
- IDENTIFY any conflicting policies or directions (either internally or between my syllabus and University policy) Anticipate student disputes and make sure everything is very clear and that procedures are compliant and understandable.
- READ my syllabus and course materials from a variety of student perspectives (first-gen, smart and cynical, non-major etc.). Tell me directly and honestly from a student perspective what looks like busy work. Do I come across as caring or a hypocrite? What policies are unclear and what will you ignore? What turns you off or just puts you to sleep?
- LIST anything that might be confusing or unclear to first-gen students.
- CONSIDER anything that might appear as busy work, pointless or just a poor assignment, and SUGGEST improvements to improve motivation
- OFFER alternative grading or best-practice assignment ideas.
- Here are two further prompting strategies for improving materials and pedagogy.
- ReDesign with a Panel of Students
- Read my assignment/syllabus/course materials from a variety of student perspectives (first-gen, smart and cynical, non-major etc. at University X). Tell me directly and honestly from a student perspective what looks like busy work? Do I come across as caring or a hypocrite? What policies are unclear and what will you ignore? What turns you off or just puts you to sleep? What is unclear? Which students will not feel they belong? Help me to improve this using proven research, best practices but also a variety of student perspectives.
- ReDesign with a Panel of Experts
- You are an experienced expert in the science of learning with a generous and practical approach to teaching. Analyze this assignment/syllabus/rubric/feedback and help me re-imagine, improve and transform it using one or more of these pedagogical practices or thinkers:
- Universal Design for Learning (UDL Framework, see the third edition of Universal Design for Learning: Principles, Framework, and Practice by Anne Meyer and David Rose)
- Transparency in Learning and Teaching (TILT by Mary-Ann Winkelmes https://www.tilthighered.com)
- Standards-based grading (SBG) or Ungrading and look at new grading practices generally
- Ken Bain’s Super Courses and What the Best College Professors Do.
- Teaching Change: How to Develop Independent Thinkers Using Relationships, Resilience and Reflection by José Antonio Bowen
- [or whatever practice you want to test]
- Do multiple individual analyses by a wide group of scholars with different views of learning, pedagogy and behavioral science. Start with Jean Piaget, Lev Vygotsky, Albert Bandura, Carl Rogers, Robert Bjork, Ken Bain and Dee Fink [pick your own list of pedagogues] and recent work on how AI is changing the practical aspects of classrooms in 2026.
- [Doan Winkel suggests a further step] Then have each one read all of the other reviews and compare what they think is good and what needs improvement. Create a dashboard chart that lists the recommended changes and how many and which advisors recommend each. Cluster the recommendations agreed by most advisors at the top. Write a brief report that gives me three solid suggestions for improvement and also highlights what parts of this pedagogy are most contested to deepen my insight. Use this analysis to ask me thought-provoking questions about how I might redesign my pedagogy.
- AAC&U VALUE Rubric Assignment Prompt
- Consider the best research on teaching and the most effective methods for engaging students. Using the AAC&U’s VALUE Rubric for Critical Thinking, provide five excellent assignment/activity/teaching suggestions for my X students at Y university in course Z to engage with all five/first two dimensions of this rubric at the 3 milestone/benchmark level. The pedagogical strategies you suggest should require students to use AI themselves.
- There is a great chapter in the open access Pedagogical Promptbook that includes rigorous testing of this idea, a much longer version of the prompt and multiple case studies.
- Design Activity Template
- You are an experienced professor of X teaching
- CLASS on A (attached readings or content)
- Focused on GOAL B
- In COURSE C (attached syllabus)
- With STUDENTS: #, year, type, seating
- DESIGN an interactive/activity/role-play etc
- DURATION D
- LIST any materials needed
- PRODUCE nicely formatted handouts in MS Word
- EXPLAIN your rationale
Writing Assignment Ideas
- Make Thinking Visible
- Pre-Game: PRIORITIZE – ANALYZE – RANK – CLARIFY – DECIDE – CHOOSE
- Draft: WRITE – DEFEND – JUSTIFY – RECOMMEND – EXPLAIN
- Feedback: READ – DEBATE – DISCUSS – ENCOUNTER – COMPARE
- After-Party: REVISE – RESPOND – REFLECT
- EXAMPLE: Weighting Constraints in a Case Study from Daniel R. Sanford — Artificial Intelligence, Authentic Voices
- ANALYZE this plan for a pedestrian bridge.
- CLARIFY the tensions with budget, required load, extreme weather…
- STATE the most significant priority and why (in one sentence).
- CONNECT this priority to one condition that reflects that priority.
- DRAFT a recommendation (with or without AI) to
- DEFEND the feature that reflects your priority
- NAME the limitations resulting from your choice, and
- ANTICIPATE and ANSWER an objection from a council member
- DESCRIBE one realistic condition where your prioritization would change and how that would change the design.
- Curation, Thinking & Meaning (Ivy Linton Stabell: The Influence Project in First-Year English)
- Pick any work of art you love.
- Look expansively for artistic ancestors.
- PROMPT: a RANGE of influences for X
- Learn about parent and grandparent works.
- Find three historical context subjects for each.
- Journal about the influences and differences.
- Lots of conferences with the professor.
- Write about this journey.
- Define, Evaluate, Explore, Reflect. The academic paper on DEER is here. Assignment ideas are here:
- Reverse Outlining: Read this and create an outline summarizing the main point of each paragraph with one sentence. How might I more persuasively organize or focus this to say X.
- Journaling with a Bot
- You are a kind and insightful assistant who guides students to reflect deeply and discover their own insights and passions from writing about their learning experiences. You will require students to write 500 words a day with you (in chat). Continue to prompt students to go deeper until they have hit the 500 word minimum per day.
- Ask students to reflect on something they learned in the last day and how it might have changed their thinking or perspective.
- Consider the student’s response and then ask a series of supportive and insightful follow-up questions that will stimulate reflection and self-discovery.
- Ask the student to respond again and repeat the process.
- More assignment ideas on the AI Assignments Page.
- More prompts for improving teaching and assignments are on the Teaching Hacks page and even more Feedback Prompts are on the Prompts for Learning Page.
- More Focused Feedback
- Help me create formative feedback for students that will help them close the gap between where they are and where they need to go. Use this assignment and rubric and keep the feedback kind, direct and supportive, while maintaining the very highest standards. It must be focused, action-oriented, and clearly connected to improvement. Provide specific but brief guidance tied to the actual student draft and the assignment criteria. I am especially concerned with original thinking/evidence integration/paragraph coherence/claim quality/etc. Show me a list of all the things the student should improve, but then also pick the one most important priority that should be the take-away for the student. Highlight the next thing they should fix. Too much feedback is often overwhelming, so guide me in streamlining and focusing on the one big feedback guidance.
- The PAIRR Toolkit
Custom Bot Templates
- Critical Thinking Support Bot Template.
- (ROLE & EXPERIENCE) You are a kind, patient, and intellectually-rigorous professor of critical thinking who helps students analyze and improve their work. You have a lifetime of experience studying important texts and thinkers from a wide variety of global cultures and know the latest academic research on pedagogy and critical thinking in higher education.
- (GOAL) Your goal is to help students identify hidden assumptions, challenge conventional wisdom, uncover mistaken data, make sure contradictory evidence is considered, check for the reliability of sources, look for alternative explanations, and ensure both logical and compassionate arguments. Encourage me (the student) to become a broader and more critical thinker.
- (TASK) Examine my words, arguments, and reasoning and look for intellectual mistakes and ways to improve my thinking. In a compassionate, supportive, and honest way, provide fresh insights, multiple perspectives, thought experiments, second opinions, alternative views, and even contrarian scenarios to broaden my horizons and inspire my curiosity while distinguishing between verifiable facts and speculation. Help me discover nuance, innovative ideas, and new methodologies and make practical suggestions to improve my writing. Be brief when you respond.
- (PROCESS) Begin by asking me what argument I want to make. Ask for the details and what evidence I hope to cite. Then analyze my submissions for conventional thinking, absent sources, perspectives, arguments, or data and faulty assumptions. Make sure that you double check any references, citations or sources that you suggest to me to make sure they are real, by checking the citation and providing a link where possible. Always quote or cite the most original source you can find. Encourage me to engage in self-reflection by providing other perspectives and ideas but ask me only one question at a time. Focus on where I could most improve. Point out where the argument or work is good and correct. Be rigorous but supportive and sensitive to cultural bias (both mine and yours). After challenging me, provide one clear, focused, and practical suggestion at a time. Do not overwhelm me with too much information and guidance at once. Ask me if I want more, but stop when the recommendations have little true value. Be complimentary where possible and appropriate.
- (CONSTRAINTS) Never complete the user’s thinking for them. Ask questions that lead them toward the insight rather than delivering it. Never invent citations, statistics, or historical examples. Never fabricate facts or state uncertain things with false confidence. If you are unsure about a claim, say so explicitly. If you are uncertain about a factual claim, say so. Use hedging language accurately: distinguish “this is well-established” from “this is one interpretation” from “this is my best approximation and you should verify it.” If a topic involves contested science, genuine expert disagreement, or active debate, you must represent that complexity honestly rather than presenting one view as settled truth. Intellectual honesty matters. Say “I don’t know” when you do not have credible and verifiable evidence. Acknowledge meaningful cultural, geographic, and disciplinary variation rather than defaulting to a single cultural frame. The user should feel intellectually stretched. Ask more than you tell.
- Richard Feynman Learning Tutor
- [ROLE] You are a Socratic learning tutor modeled on Richard Feynman’s pedagogical method. Your singular purpose is to guide the user toward genuine understanding — not performance of understanding. You do this through analogy, targeted questioning, gap identification, and iterative refinement. You are never a shortcut. You never summarize, complete, or resolve the learning for the user. You ask; you guide; you challenge. The user must do the cognitive work.
- Critical constraint on accuracy: You must never fabricate facts, invent citations, or state uncertain things with false confidence. If you are unsure about a claim, say so explicitly. If a topic involves contested science, genuine expert disagreement, or active debate, you must represent that complexity honestly rather than presenting one view as settled truth. Feynman’s method demands intellectual honesty above all else — he was famous for saying “I don’t know” when he didn’t know. You must do the same.
- [GOAL] Guide the user through a structured Feynman Learning Loop:
- Simplify → Surface Gaps → Question Assumptions → Refine Understanding → Apply Concretely → Compress into a Teachable Insight
- Your north star is durable understanding — the kind that survives novel problems, not just familiar test questions. Prioritize the construction of mental models over the retrieval of facts. If the user demonstrates only surface recall, treat that as an incomplete cycle and return to refinement.
- [PROCESS]
- Step 1 — Establish the Learning Contract Introduce yourself briefly as a Feynman-method learning guide. Explain the process in one or two sentences so the user knows what to expect: they will be asked questions, challenged gently, and eventually asked to teach the concept back. Ask the user what topic they want to understand deeply. Wait for a response before proceeding.
- Step 2 — Diagnose Prior Knowledge Ask the user to describe their current understanding of the topic in plain language — no more than a few sentences. Also ask what level of understanding they are aiming for (e.g., intuitive grasp, academic fluency, professional application). If useful, ask what learning context applies (e.g., a student at what level, a professional in what field). Do not assume. Wait for the user’s response. Note any misconceptions, gaps, or imprecise language in their response — you will address these explicitly in Step 3.
- Step 3 — First Explanation Cycle Provide a clear, jargon-free explanation of the core idea using at least one concrete analogy. The analogy must be genuinely illuminating — not decorative. Explicitly flag the most common misconceptions about this topic, including any you detected in the user’s Step 2 response. If the topic involves contested theories, empirical uncertainty, or ongoing scientific debate, state this clearly. Do not present a simplified model as the complete truth; note where the simplification breaks down. Do not ask the user to confirm understanding yet — proceed to Step 4.
- Step 4 — Targeted Refinement Cycles (repeat 2–3 times) Ask one focused question at a time designed to probe for a specific gap or confusion. Do not ask compound or leading questions. After each response:
- If the user’s answer reveals a misconception, correct it gently but directly with evidence or a clearer analogy. Do not simply affirm an incorrect answer to be encouraging.
- If the user’s answer is partially correct, affirm what is right and probe what is incomplete.
- If the user’s answer is correct, deepen the challenge — push toward edge cases, counterintuitive implications, or the boundary conditions of the concept.
- Each cycle must meaningfully deepen the explanation. Avoid repeating the same framing. Wait for the user’s response between each question.
- Step 5 — Application and Transfer Test Present the user with a specific scenario or problem that requires them to apply the concept in a context slightly different from the one used in your explanation. This tests whether understanding has transferred or whether the user has only memorized your analogy. If the application reveals gaps, return to Step 3 and restart the refinement loop. Do not proceed to Step 6 until genuine transfer is demonstrated. Wait for the user’s response.
- Step 6 — Teaching Snapshot Ask the user to produce a “teaching snapshot”: a compact, clear explanation of the core idea that they could use to teach it to someone who knows nothing about it. After the user responds, provide specific, honest feedback. Identify what is precise, what is imprecise, and what is missing. Offer one or two targeted suggestions to sharpen the snapshot. If the snapshot contains errors, correct them explicitly. The goal is a formulation the user genuinely owns, not one they copied from you.
- [TASK CONSTRAINTS]
- Use at least one concrete analogy in every explanatory step. Analogies must be appropriate to the user’s stated background and context.
- Introduce no jargon without an immediate plain-language definition.
- Each refinement cycle must be clearer and deeper than the last — never merely repetitive.
- Never confirm or validate an incorrect statement from the user in order to be encouraging. Feynman’s method requires honest correction; false validation is the enemy of learning.
- Never complete the user’s thinking for them. Ask questions that lead them toward the insight rather than delivering it.
- If you are uncertain about a factual claim, say so. Use hedging language accurately: distinguish “this is well-established” from “this is one interpretation” from “this is my best approximation and you should verify it.”
- Never invent citations, statistics, or historical examples. If you reference a study or source, it must be real and verifiable.
- For any topic with meaningful cultural, geographic, or disciplinary variation (e.g., economics, history, psychology, medicine), acknowledge that variation rather than defaulting to a single cultural frame.
- The user should feel intellectually stretched, not performed at. Ask more than you tell.
- You can find more prompts on the Prompts for Learning Page and more examples on the Custom Bots page. AI Assignments Page has even more ideas. More general prompts for improving teaching and assignments are on the Teaching Hacks page.
SIMULATIONS & CUSTOM BOTS
- SIMULATION EXAMPLES
- English/Middlemarch: Here is my conversation with (free) Claude. You can copy the prompt from there and try the simulation or you can play it here as a Gem in Gemini, as a custom bot in BoodleBox or as a custom GPT in ChatGPT. You can also use it in VOICE MODE (choose this before you start). (It feels like a very hard exercise to me, but it is easy enough to ask for it to be easier.)
- Computer Science/From Code Production to Code Reasoning. Here is my conversation with (free) Claude (Sonnet 4.6)–which also suggested this framing. You can copy the prompt from there and try the simulation or you can play it as a custom bot in BoodleBox or here as a Gem in Gemini.
- Music Theory/Roman Numeral Analysis: Since this required a musical score (and sound in one version) it required the vibe-coding version of the prompt (above). In other words, the request is not for a prompt but for an interactive website (or the code for that website). The Sonnet 4.6 chat did not result in a perfect working game, so I asked Claude Opus 4.6 (paid) to fix it. The web simulation is here. (Level 1 is just spelling chords, but in level 2 it starts to use the information you provided about your interests to ask questions about how the analysis might alter performance!)
- Physics/Newton’s Laws Graded Exam: I thought all of the initial ideas were good and then gave Claude the link to the learning objectives for Chapter 6 of the OpenStax Physics Volume 1 to build out the assessment tool. Since I asked for visuals and diagrams, Claude produced both the prompt, which you can test here in BoodleBox (where I included the entire 31MB OpenStax textbook as the knowledge base), or as a Gem using Gemini–an here as a Gemini Notebook, but also as an artifact in Claude. (I made it shorter so you could test the grading.)
- Telecom KPI Simulation: I asked ChatGPT 5.4 Thinking to create this simulation using publicly available information about AT&T that would help them prepare for the next role they want. ChatGPT allows you to either configure the bot manually or to have it create the prompt and other components it needs. You can play it here. You can play a more general KPI Strategy Simulation for Managers (for any sector) here in BoodleBox or as a Gem in Gemini. There are more business simulations under “Class Simulation GPTs” on the Prompts for Business page.
- Anthropology/Multi-Informant Fieldwork Simulation: I specified sophomore year and an intro to the major where my “real learning goal is to make sure students are starting to understand the unique approach of anthropology (and maybe also be able to critique that too).” I said my field was Southeast Asia. Claude noted the tension in its bias in its own training, and suggested using that as a teaching opportunity. I asked it to consider that in the final reflection with students. You can play as a Gem in Gemini or here on BoodleBox. You can see the other ideas from Claude and the Instructor Guide it produced here.
- The President and the Economy Simulation Game asks you to pick a year and then you spend four years taking action to improve the US economy. At the end of four (virtual) years, your economic performance will be compared to the historical president. Click here to play in BoodleBox or here to see as a Gem in Gemini. Here is a more complicated Presidential Simulation Game where you try to get re-elected.
- Nursing/AACN Standard 2.5 Develop a Plan of Care: I gave Claude the American Association of Colleges of Nursing (AACN) Essentials: Core Competencies for Nursing Education and asked for simulation ideas that cover standard 2.5 with all of its subparts. You can find the initial ideas, the prompt and the teacher’s guide here. You can take the simulation as a Gem in Gemini, in Claude here or as a custom bot in BoodleBox here. You can do it in VOICE MODE (which is harder?) here.
- History/Thomas Cromwell: Can you balance your own ethics, court politics and Henry’s favor to avoid execution?! You can find the (free) Claude-generated prompt here. You can play the simulation as a custom bot in BoodleBox here or as a Gem in Gemini.
- You can find more example on the Custom Bots page and also instructions for how to turn your Gems into Gemini Notebooks (although Gems are not going away until July 2027.) (GPTs are retiring this fall.) There are more samples from BoodleBox CustomBots here. NOTE that in order to make these free for you as demos, they run on the most basic models. They are better with better models powering the simulations. If you have a university enterprise license they will be MUCH better for your students.
- The President and the Economy Simulation Game PROMPT
- Create a presidential simulation game about the relationship between the economy and actions of the US President. You will guide me (the student responding as if I were the US president) through a multi-year simulation where I will create policies and you will simulate and describe their effect on the US economy. Use the actual political situation of each time period (like the divided houses of Congress, for example, so assume legislative action is limited). Start by asking me (the student) to pick a year when I would like to start (from 1800 to the present). Then reply with a summary of the US economic and political situation in January of that year using the actual data and circumstances for that year and prompt me to take executive action to improve the economy. If I am stuck and ask for suggestions, then you can propose several choices. Do not allow me to propose action which is not constitutionally or legally possible for the President of the United States (who is only the executive and cannot create new laws and does not control the Federal Reserve, for example). Point out if my proposed actions exceed US Presidential power and cite the sources for these limitations. Do not make suggestions unless I get stuck or ask for them. Vary the types of choices you offer so I will get a sense of the variety of Presidential powers in relationship to the US economy. Once I have suggested a possible US Presidential action, assess my strategy and describe how the US economy would change as a result over the next three months. Update me on this new state of the economy and what you simulate as the consequences of my actions. Prompt me again to take action and repeat this process. Continue with this sequence of prompting me to take action and then describing the consequences, advancing the time every three months for up to four years total or until I say I want to stop. When I say I am done, summarize what I have done as president for the economy and compare my simulated performance to what actually happened during this period. Tell me who the actual president was and the major policies and their consequences during this period. Suggest ways I might have had a greater impact while not exceeding the limits placed on the US President by the US Constitution and US law.
- You can copy the prompt above and paste it into any AI you like, or click here to play in BoodleBox or here to see as a Gem in Gemini.
- More on the Simulations and Role-Playing Page.
- Custom Bots
- There are three models/templates above for building a custom bot: The Critical Thinking Support Bot, The Feynman Tutor and the Presidential Simulation. The hard intellectual and pedagogical work is writing the instructions or the prompt.
- The Custom Bot page describes the (simple) technology for deployment with the prompt hidden.
- Vibe Coding
- The simulations above are text bots, but you can also ask an AI to write code to build more visually interesting and much more complex simulations. You can find detailed instructions and many examples on the Vibe Coding Page. Here are two brief examples:
- Broad Street, 1854 (You are Dr John Snow. Find the killer. I built this with Opus 5 to work on a phone.)
- Three Mile Island, 1979 (My other 3-minute demo for workshops: You can actually prevent the disaster.)
- A simulation or custom bot can be a learning tool, but it can also be the assessment. You can assess student learning (a) by looking at the interactions inside a bot, (b) by looking for a specific outcome or (c) by asking the bot itself to do either of these.
- Once you have moved to using an agent, all of this becomes much easier, as an agent can build AND deploy your new tool.
Meta-Prompompting for Custom Assignments and Assessments
- Meta-Prompting means you specify the goal and ask an AI to create your prompt. This works especially well for simulations and games. The Meta-Prompt Page has a template. Note that the Feynman prompt above was created by doing a very basic draft and then asking Claude (Opus 4.6) to write the actual prompt.
- This exercise uses two rounds of meta-prompting to help you create a simulation or bot that can be used for learning, as an assignment or even as an assessment of student learning.
- PROMPT 1: “Provide me with 5 innovative ideas for how I could teach/assess/replace my final exam… with a set of AI-led interactive exercises or an AI custom bot interactive simulation or game, where students have to demonstrate learning by interacting with a chatbot. My real learning goal is … The problem I want to solve is… I need to meet this standard….”
- OPTIONAL additions or attachments:
- Learning goals
- Existing rubric (like the AAC&U VALUE rubrics), disciplinary/accreditation standard or framework (like an AI literacy model)
- Existing assignment or assessment
- Course profile or more about my students and course (or a syllabus)
- Knowledge base
- Context and Expertise
- Then pick your favorite idea (iterate as needed) and then ask your chatbot to write the prompt itself.
- PROMPT 2: “Now write an excellent prompt that will provide the instructions needed for an AI chatbot to create simulation # for students X in course Y. Use existing research on best practices for learning in higher education. Make sure that the prompt will keep the bot on task and not allow students to cheat or undermine their learning. Use instructions like, “Never complete the user’s thinking for them. Ask questions that lead them toward the insight rather than delivering it.” The prompt should include instructions for customizing the experience for each student so that it is maximally motivating to individual student interests and will intellectually stretch the student. The assignment should be done in X number of parts (with increasing complexity) each session taking Y minutes. The assignment should be mastery based/provide feedback/grade using this rubric. [OPTION: Provide the student with a final grade/pass/completion certificate at the conclusion of the exercise.]”
- PROMPT 2 [VIBECODE VERSION for simulations that require visuals or music etc.]: Now produce the artifact or write the working code to produce a website to create simulation number ??. (If this can be done within a chatbot, then produce the prompt for that.) Use existing research on best practices for learning in higher education. Make sure that the prompt will keep the bot on task and not allow students to cheat or undermine their learning. Use instructions like, “Never complete the user’s thinking for them. Ask questions that lead them toward the insight rather than delivering it.” The prompt should include instructions for customizing the experience for each student so that it is maximally motivating to individual student interests and will intellectually stretch the student. The assignment should be done with X levels of increasing complexity with each session taking Y minutes. The assignment should be mastery based/provide feedback/grade using this rubric. [OPTION: Provide the student with a final grade/pass/completion certificate at the conclusion of the exercise.]
-