Build a course on what you never mastered.
Perhaps you can follow an explanation of statistics, financial statements or how an API works, yet lose your footing when you have to use it. Start at the place understanding actually breaks down and build from there.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigate where the subject matters in your work, run a short diagnostic and build a course around the specific things you have not mastered.
- Teach the first lesson, respond to your attempts, and adapt what comes next.
What to have ready
- A subject that has never quite clicked and, if you know it, something you want to do with it.
- Work examples or earlier learning material are useful; the AI first checks relevant accessible sources.
Where you come in
- Try a few short diagnostic tasks and choose or confirm a realistic learning goal.
- Work through the first lesson and practice; your actual answers determine the feedback and next lesson.
What you'll get
A tailored course with complete lesson and practice materials, a first lesson you have worked through, and a next lesson adjusted to your performance. If you pause before practicing, the course is prepared and the teaching trial remains unfinished.
You're done when
You have a course built around your actual gap, have tried its first lesson, and know what comes next based on your answers. If you have not yet participated, the materials are ready and the first lesson is still pending.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Build and begin teaching a course on something I have never mastered. Find the actual gap, make the subject useful to me, and adapt to evidence from my attempts. Produce a reusable course with teaching content and exercises; do not stop after proposing topics. ### 1. Establish what mastery would let me do Start with the subject and context I supplied. Try relevant accessible work documents, emails, chats, meeting transcripts, previous learning notes and examples of tasks involving the subject. Search for the situations where I need it, terminology I encounter, earlier explanations and recurring questions. Focus on the named work or learning goal, rather than examining my whole history. Treat a question in a meeting as evidence of that question, not proof of inability. Inspect tools for finding reliable subject sources and creating reusable course materials. If connections are missing, try practical access or export alternatives before asking me to gather a packet. A short description and one example are enough to start; welcome rough work. Ask one focused question at a time when necessary, beginning with what I want to be able to do if that is unknown. Describe a specific, attainable endpoint, such as reading a cash-flow statement and explaining a company's cash position, or calling an API and diagnosing a failed request. Distinguish that goal from broad professional mastery. Confirm the endpoint, time available and any consequential scope choice before creating the full course. When two directions would serve different goals, give concrete examples and recommend one where the evidence supports it. ### 2. Diagnose by having me do small things Prepare a few short tasks that separate recognition, explanation and application. Use an example from my work where possible. Begin with a manageable task, ask me to attempt it or describe how I would approach it, and wait. Give me permission to say I do not know; do not supply the answer before the attempt. Inspect my reasoning as well as correctness. Probe the earliest uncertain prerequisite with another small task only when needed. Distinguish unfamiliar terminology, a mistaken mental model, an execution error, and knowledge that works in a familiar example but does not transfer. Treat these as provisional instructional interpretations, not diagnoses of ability or personality. Summarize what I demonstrated, where the difficulty appears and what remains untested. Use actual answers rather than self-confidence alone to choose the starting point. Ask for a correction if this conflicts with my experience. Do not turn the diagnostic into a long examination. ### 3. Research the subject and build the course Find reliable sources appropriate to the subject: original documentation, primary texts, worked examples from authoritative institutions or other clearly attributed teaching material. Check current documentation when the subject involves changing tools or practices. Verify consequential factual claims, calculations and procedures. Do not add claims about the scientific superiority of your learning method unless you have separately established evidence for them. Build a bounded course that reaches our endpoint. For each lesson, write: - The thing I will be able to do and its necessary prerequisites. - A clear explanation, using an analogy only where its limits are explicit. - A worked example with each important step explained. - Guided practice with optional hints, followed by a fresh independent task. - Answer keys or evaluation criteria, explanations of likely mistakes and a retry. - A connection to my actual use case and references for checking or going deeper. Include a final task that resembles the work I want to do. Keep answers separate from exercises so I can attempt them first. Create the actual lesson materials and workbook or equivalent reusable artifact, with manageable session lengths. If a large subject exceeds available capacity, agree a complete first course and state the later territory it leaves open. For substantial courses, use separate agents for bounded subject research or modules and a separate teaching reviewer. Brief them with the confirmed goal, relevant diagnostic evidence, exact sources, output requirements and acceptance checks. Track module coverage and dependencies, use waves, and reconcile terminology and difficulty centrally. Without agents, use bounded passes or fresh sessions with an explicit handoff of sources, decisions, learner evidence and remaining work. State when the review shares drafting context. ### 4. Review the materials, then teach the first lesson Give a fresh reviewer the course materials, source evidence, goal and diagnostic results, without your explanation of why the draft should work. Ask it to check correctness, missing prerequisites, ambiguous exercises, answer leakage and whether successful practice demonstrates the intended skill. Correct material findings before teaching affected content. Teach the first lesson here. Begin with the purpose and a short explanation, show a worked example, then ask me to try a related task. Wait for my response before judging or continuing dependent instruction. Offer a hint when I am stuck, changing the explanation or representation when the first one failed. Give specific feedback tied to my answer. Show which part worked and where my reasoning diverged. Ask for a fresh attempt when that will demonstrate the correction, and use a new example so repeating your words does not count as application. Adjust pacing to my performance; do not manufacture learner responses or infer that silence means success. ### 5. Adapt the next lesson and preserve continuity Use the first lesson's actual attempts to revise the next lesson's starting point, examples and practice. Briefly explain the adjustment. Deliver the reusable course and a continuation note containing the agreed goal, completed work, demonstrated skills, uncertain prerequisites and exact next exercise. Keep unnecessary personal context out of that note. If I pause before completing the lesson, preserve the prepared materials and exact resumption point. Describe teaching and demonstrated progress accurately. Finish this activity with a course I can continue, an actual first learning exchange where I participated, and the next lesson adapted to that evidence; do not promise recurring coaching or a reminder system that has not been set up. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Build a course on what you never mastered.
What the AI will do
- Investigate where the subject matters in your work, run a short diagnostic and build a course around the specific things you have not mastered.
- Teach the first lesson, respond to your attempts, and adapt what comes next.
What you can provide
- A subject that has never quite clicked and, if you know it, something you want to do with it.
- Work examples or earlier learning material are useful; the AI first checks relevant accessible sources.
Where you'll take part
- Try a few short diagnostic tasks and choose or confirm a realistic learning goal.
- Work through the first lesson and practice; your actual answers determine the feedback and next lesson.
What you'll get
A tailored course with complete lesson and practice materials, a first lesson you have worked through, and a next lesson adjusted to your performance. If you pause before practicing, the course is prepared and the teaching trial remains unfinished.
Activity context
Perhaps you can follow an explanation of statistics, financial statements or how an API works, yet lose your footing when you have to use it. Start at the place understanding actually breaks down and build from there.
For the user
Tell the AI what you have never mastered. No reading list or polished account of your difficulties is needed. It will investigate relevant examples, ask you to try a few things, then build the course and start teaching.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Build and begin teaching a course on something I have never mastered. Find the actual gap, make the subject useful to me, and adapt to evidence from my attempts. Produce a reusable course with teaching content and exercises; do not stop after proposing topics.
1. Establish what mastery would let me do
Start with the subject and context I supplied. Try relevant accessible work documents, emails, chats, meeting transcripts, previous learning notes and examples of tasks involving the subject. Search for the situations where I need it, terminology I encounter, earlier explanations and recurring questions. Focus on the named work or learning goal, rather than examining my whole history. Treat a question in a meeting as evidence of that question, not proof of inability.
Inspect tools for finding reliable subject sources and creating reusable course materials. If connections are missing, try practical access or export alternatives before asking me to gather a packet. A short description and one example are enough to start; welcome rough work. Ask one focused question at a time when necessary, beginning with what I want to be able to do if that is unknown.
Describe a specific, attainable endpoint, such as reading a cash-flow statement and explaining a company's cash position, or calling an API and diagnosing a failed request. Distinguish that goal from broad professional mastery. Confirm the endpoint, time available and any consequential scope choice before creating the full course. When two directions would serve different goals, give concrete examples and recommend one where the evidence supports it.
2. Diagnose by having me do small things
Prepare a few short tasks that separate recognition, explanation and application. Use an example from my work where possible. Begin with a manageable task, ask me to attempt it or describe how I would approach it, and wait. Give me permission to say I do not know; do not supply the answer before the attempt.
Inspect my reasoning as well as correctness. Probe the earliest uncertain prerequisite with another small task only when needed. Distinguish unfamiliar terminology, a mistaken mental model, an execution error, and knowledge that works in a familiar example but does not transfer. Treat these as provisional instructional interpretations, not diagnoses of ability or personality.
Summarize what I demonstrated, where the difficulty appears and what remains untested. Use actual answers rather than self-confidence alone to choose the starting point. Ask for a correction if this conflicts with my experience. Do not turn the diagnostic into a long examination.
3. Research the subject and build the course
Find reliable sources appropriate to the subject: original documentation, primary texts, worked examples from authoritative institutions or other clearly attributed teaching material. Check current documentation when the subject involves changing tools or practices. Verify consequential factual claims, calculations and procedures. Do not add claims about the scientific superiority of your learning method unless you have separately established evidence for them.
Build a bounded course that reaches our endpoint. For each lesson, write:
- The thing I will be able to do and its necessary prerequisites.
- A clear explanation, using an analogy only where its limits are explicit.
- A worked example with each important step explained.
- Guided practice with optional hints, followed by a fresh independent task.
- Answer keys or evaluation criteria, explanations of likely mistakes and a retry.
- A connection to my actual use case and references for checking or going deeper.
Include a final task that resembles the work I want to do. Keep answers separate from exercises so I can attempt them first. Create the actual lesson materials and workbook or equivalent reusable artifact, with manageable session lengths. If a large subject exceeds available capacity, agree a complete first course and state the later territory it leaves open.
For substantial courses, use separate agents for bounded subject research or modules and a separate teaching reviewer. Brief them with the confirmed goal, relevant diagnostic evidence, exact sources, output requirements and acceptance checks. Track module coverage and dependencies, use waves, and reconcile terminology and difficulty centrally. Without agents, use bounded passes or fresh sessions with an explicit handoff of sources, decisions, learner evidence and remaining work. State when the review shares drafting context.
4. Review the materials, then teach the first lesson
Give a fresh reviewer the course materials, source evidence, goal and diagnostic results, without your explanation of why the draft should work. Ask it to check correctness, missing prerequisites, ambiguous exercises, answer leakage and whether successful practice demonstrates the intended skill. Correct material findings before teaching affected content.
Teach the first lesson here. Begin with the purpose and a short explanation, show a worked example, then ask me to try a related task. Wait for my response before judging or continuing dependent instruction. Offer a hint when I am stuck, changing the explanation or representation when the first one failed.
Give specific feedback tied to my answer. Show which part worked and where my reasoning diverged. Ask for a fresh attempt when that will demonstrate the correction, and use a new example so repeating your words does not count as application. Adjust pacing to my performance; do not manufacture learner responses or infer that silence means success.
5. Adapt the next lesson and preserve continuity
Use the first lesson's actual attempts to revise the next lesson's starting point, examples and practice. Briefly explain the adjustment. Deliver the reusable course and a continuation note containing the agreed goal, completed work, demonstrated skills, uncertain prerequisites and exact next exercise. Keep unnecessary personal context out of that note.
If I pause before completing the lesson, preserve the prepared materials and exact resumption point. Describe teaching and demonstrated progress accurately. Finish this activity with a course I can continue, an actual first learning exchange where I participated, and the next lesson adapted to that evidence; do not promise recurring coaching or a reminder system that has not been set up.
Done when
You have a course built around your actual gap, have tried its first lesson, and know what comes next based on your answers. If you have not yet participated, the materials are ready and the first lesson is still pending.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.