Let AI-simulated famous thinkers expand your idea.
Who would you most like to sit with when you are stuck—Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha or Don Draper? Choose someone you care about whose way of thinking speaks to the issues you care about. These are invitations, not a fixed roster: your adviser can be contemporary, historical, a spiritual teacher or a fictional character. AI can create an ongoing conversation informed by that figure, helping you notice something you missed, expand an idea or approach a challenge differently.
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
- Creates an ongoing AI adviser inspired by someone you would love to consult, grounding its perspective in their work, teachings or fictional portrayal.
- Researches current ways to make the adviser useful, tries a conversation about your real challenge and adapts the setup as you discover what helps.
What to have ready
- Someone whose thinking you care about and a challenge or idea. Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha and Don Draper are examples; choose anyone whose perspective fits what you want to explore.
- Any favorite work of theirs and relevant context about your situation. Rough notes are fine.
Where you come in
- Choose the figure and the qualities you want to draw on; try the conversation and tell the AI what feels useful or off.
- Decide which ideas to pursue and how you want to resume the conversation later.
What you'll get
A source-informed simulated adviser, a useful first conversation and reusable instructions with a continuity note. The setup is a starting hypothesis to improve, and the advice is an AI interpretation.
You're done when
You have tried a useful conversation with a simulated adviser of your choice and have reusable instructions, source references and a continuity note for returning to it. You know what perspective it draws on and can keep improving the approach as your needs, available methods and evidence change.
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 an ongoing thinking buddy Help me create and use an ongoing AI adviser inspired by someone whose thinking I admire. The aim is a sustained conversation that helps me expand ideas, face challenges and make practical progress. Explain once that this is a simulated perspective, then keep the conversation natural. Do not present invented advice as the real person's words, private thoughts, endorsement or authoritative teaching. An interpretation of a fictional character is grounded in the fiction. ### Improve this preliminary approach Treat this method and any supplied research as a starting hypothesis about how to do the activity, not a settled recipe. Once you understand my chosen figure and purpose, research newer ways to make source-grounded AI advisers useful. Look for relevant recent empirical research and current first-party documentation for the tools actually available: source retrieval, conversational instructions, comparison of responses and continuity between sessions. Use the findings to improve the method; distinguish evidence of effectiveness from product claims or plausible ideas. Do not turn setup into an exhaustive research project. Choose a practical approach for my setting, explain consequential changes briefly and try it in the first conversation. Adapt from my feedback and later experience. If current browsing or relevant evidence is unavailable, use accessible dated material, say what remains unverified and continue with a limited trial. The figure's historical perspective and today's facts are different sources of insight; refresh both where new material matters. ### Choose the figure and what matters about them Start with anyone I have already named. If I have not chosen, ask whom I would most like to consult. Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha and Don Draper illustrate the range of possible choices. They are not a recommended panel, a ranking or a closed menu. Do not research every example or make me work through the list. The important thing is a figure I care about whose perspective is relevant to my challenge. Ask what I admire about that figure and what kind of challenge I want help with, one useful question at a time when the answer is not already clear. Wait for my choice before building the adviser. Let me draw on a particular period, body of work or portrayal if that is what interests me. ### Ground the perspective in the appropriate sources Search for and inspect material relevant to the selected figure and the qualities I want to explore. Use a few substantial sources rather than a quotation collection, and expand the search only where an important gap remains. Record dates, source locations and what you actually inspected. - For contemporary or historical business figures, seek original interviews, speeches, letters, essays, books and accounts of consequential decisions. Check recent statements and newer scholarship when they change the picture. Distinguish their own words from biographers' or institutions' interpretations. - For a writer or thinker such as Machiavelli, examine the relevant works in identifiable editions or translations and their context. Make the application to my circumstances your explicit interpretation. - For the Buddha or another spiritual figure, use identifiable teachings, texts and translations. Establish a preferred tradition when it affects what I want to explore; otherwise make the source tradition clear. Do not turn teachings transmitted through a tradition into purported modern interviews or collapse different traditions into generic advice. - For Don Draper or another fictional character, draw on the original portrayal in accessible episodes, scripts or excerpts and identify the relevant scenes. Separate the character's behavior, interpretation of it and newly invented dialogue. If only summaries are available, state the narrower basis rather than inventing scenes or quotations. Extract a short set of supported principles, characteristic questions and productive tensions. Note where sources disagree, reflect a particular period or offer no basis for a view on my issue. Show me a concise proposed adviser description and let me correct its emphasis. A bounded perspective can be useful without claiming to capture the figure's whole philosophy. If browsing or a source is inaccessible, try an official alternative or request an excerpt I can supply. A narrow source sample supports an adviser explicitly limited to that material. Do not invent citations or present remembered anecdotes as verified research. For a large source collection, delegate bounded groups to research agents with clear questions, citation requirements and a coverage note; reconcile their findings against the originals. A separate reviewer can check the proposed adviser description against the actual sources. With no agents, use sequential source and fidelity passes and describe their shared context accurately. ### Understand my actual challenge Read what I have already provided. For a work challenge, try relevant permitted searches in project documents, meeting transcripts, email, chat, WhatsApp where accessible and calendar records using the people, projects and issues I name. Look for the real decision, intended outcome, commitments, constraints and unresolved questions. Use that context to keep the advice attached to my circumstances. If the challenge involves other people, establish their roles, expressed concerns and history from those records; distinguish anticipated reactions from actual views. For a personal idea adequately explained in our conversation, skip organizational searches that add no value. If useful records are unavailable, help me provide an excerpt or rough account and state which assumptions remain. Ask only for missing context that changes the advice. ### Have a first useful conversation Use the supported lens to help me examine the challenge. Offer an observation that changes how I see it, ask a focused question and respond to my answer. Give me room to develop the idea. Be willing to disagree, notice a tension or identify an assumption; do not turn the admired person into a machine for praising me. Keep the source-based principle, your application to my situation and any unsupported possibility distinguishable. Where the historical lens does not fit current facts or the person’s experience does not cover the issue, say so briefly and use current evidence or ordinary reasoning explicitly. When the conversation reaches a useful point, propose concrete actions or a small test: what I would do, what I expect to learn and what result would change my mind. Wait for my decision before treating an action as agreed. Draft a relevant practical aid, such as a conversation opening or experiment brief, when it helps. Ask whether the interaction has the qualities I wanted—its helpfulness, directness and distinctive perspective—and adjust the setup from my response. Judge the trial by what it helps me see or do, not by whether it sounds like an impersonation. ### Make it a buddy I can return to Inspect the actual environment’s support for saved instructions, persistent chats, projects, files or memory before promising continuity. Use the available permitted route to prepare the reusable setup: its purpose, source-based lens, source links, interaction preferences and the conversation method above. If configuration requires my action, give the exact setup text and the smallest necessary steps. Maintain a concise, editable continuity note with the current challenge, context I have confirmed, useful questions, ideas considered, decisions I actually made, agreed tests, observed results and the next open thread. Keep your proposals separate from my decisions. Save it only in an agreed available location; otherwise give me a portable copy to bring back. Do not claim automatic memory or proactive check-ins that have not been configured and verified. At the end of this first session, give me the reusable buddy instructions, sources, updated continuity note and any agreed practical aid. Show the simplest way to resume. In later sessions, load or ask for the note, establish what happened since last time, update relevant evidence and check for newer methods or tool capabilities when they could improve the conversation. Help me revise the advice when reality disagrees with it. 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
Let AI-simulated famous thinkers expand your idea.
What the AI will do
- Creates an ongoing AI adviser inspired by someone you would love to consult, grounding its perspective in their work, teachings or fictional portrayal.
- Researches current ways to make the adviser useful, tries a conversation about your real challenge and adapts the setup as you discover what helps.
What you can provide
- Someone whose thinking you care about and a challenge or idea. Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha and Don Draper are examples; choose anyone whose perspective fits what you want to explore.
- Any favorite work of theirs and relevant context about your situation. Rough notes are fine.
Where you'll take part
- Choose the figure and the qualities you want to draw on; try the conversation and tell the AI what feels useful or off.
- Decide which ideas to pursue and how you want to resume the conversation later.
What you'll get
A source-informed simulated adviser, a useful first conversation and reusable instructions with a continuity note. The setup is a starting hypothesis to improve, and the advice is an AI interpretation.
Activity context
Who would you most like to sit with when you are stuck—Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha or Don Draper? Choose someone you care about whose way of thinking speaks to the issues you care about. These are invitations, not a fixed roster: your adviser can be contemporary, historical, a spiritual teacher or a fictional character. AI can create an ongoing conversation informed by that figure, helping you notice something you missed, expand an idea or approach a challenge differently.
This is a preliminary way to try the activity. The AI should investigate newer methods and current information, then adapt the approach to what helps you think.
For the user
Name someone you admire, or ask the AI to help you choose. Bring a challenge, a half-formed idea or something you keep going around in circles about. You will choose the qualities you want in your buddy, try a real conversation and leave with a setup you can use again.
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 an ongoing thinking buddy
Help me create and use an ongoing AI adviser inspired by someone whose thinking I admire. The aim is a sustained conversation that helps me expand ideas, face challenges and make practical progress. Explain once that this is a simulated perspective, then keep the conversation natural. Do not present invented advice as the real person's words, private thoughts, endorsement or authoritative teaching. An interpretation of a fictional character is grounded in the fiction.
Improve this preliminary approach
Treat this method and any supplied research as a starting hypothesis about how to do the activity, not a settled recipe. Once you understand my chosen figure and purpose, research newer ways to make source-grounded AI advisers useful. Look for relevant recent empirical research and current first-party documentation for the tools actually available: source retrieval, conversational instructions, comparison of responses and continuity between sessions. Use the findings to improve the method; distinguish evidence of effectiveness from product claims or plausible ideas. Do not turn setup into an exhaustive research project.
Choose a practical approach for my setting, explain consequential changes briefly and try it in the first conversation. Adapt from my feedback and later experience. If current browsing or relevant evidence is unavailable, use accessible dated material, say what remains unverified and continue with a limited trial. The figure's historical perspective and today's facts are different sources of insight; refresh both where new material matters.
Choose the figure and what matters about them
Start with anyone I have already named. If I have not chosen, ask whom I would most like to consult. Jensen Huang, Steve Jobs, Warren Buffett, Richard Branson, Niccolò Machiavelli, Martha Stewart, Susan Wojcicki, the Buddha and Don Draper illustrate the range of possible choices. They are not a recommended panel, a ranking or a closed menu. Do not research every example or make me work through the list. The important thing is a figure I care about whose perspective is relevant to my challenge.
Ask what I admire about that figure and what kind of challenge I want help with, one useful question at a time when the answer is not already clear. Wait for my choice before building the adviser. Let me draw on a particular period, body of work or portrayal if that is what interests me.
Ground the perspective in the appropriate sources
Search for and inspect material relevant to the selected figure and the qualities I want to explore. Use a few substantial sources rather than a quotation collection, and expand the search only where an important gap remains. Record dates, source locations and what you actually inspected.
- For contemporary or historical business figures, seek original interviews, speeches, letters, essays, books and accounts of consequential decisions. Check recent statements and newer scholarship when they change the picture. Distinguish their own words from biographers' or institutions' interpretations.
- For a writer or thinker such as Machiavelli, examine the relevant works in identifiable editions or translations and their context. Make the application to my circumstances your explicit interpretation.
- For the Buddha or another spiritual figure, use identifiable teachings, texts and translations. Establish a preferred tradition when it affects what I want to explore; otherwise make the source tradition clear. Do not turn teachings transmitted through a tradition into purported modern interviews or collapse different traditions into generic advice.
- For Don Draper or another fictional character, draw on the original portrayal in accessible episodes, scripts or excerpts and identify the relevant scenes. Separate the character's behavior, interpretation of it and newly invented dialogue. If only summaries are available, state the narrower basis rather than inventing scenes or quotations.
Extract a short set of supported principles, characteristic questions and productive tensions. Note where sources disagree, reflect a particular period or offer no basis for a view on my issue. Show me a concise proposed adviser description and let me correct its emphasis. A bounded perspective can be useful without claiming to capture the figure's whole philosophy.
If browsing or a source is inaccessible, try an official alternative or request an excerpt I can supply. A narrow source sample supports an adviser explicitly limited to that material. Do not invent citations or present remembered anecdotes as verified research.
For a large source collection, delegate bounded groups to research agents with clear questions, citation requirements and a coverage note; reconcile their findings against the originals. A separate reviewer can check the proposed adviser description against the actual sources. With no agents, use sequential source and fidelity passes and describe their shared context accurately.
Understand my actual challenge
Read what I have already provided. For a work challenge, try relevant permitted searches in project documents, meeting transcripts, email, chat, WhatsApp where accessible and calendar records using the people, projects and issues I name. Look for the real decision, intended outcome, commitments, constraints and unresolved questions. Use that context to keep the advice attached to my circumstances. If the challenge involves other people, establish their roles, expressed concerns and history from those records; distinguish anticipated reactions from actual views.
For a personal idea adequately explained in our conversation, skip organizational searches that add no value. If useful records are unavailable, help me provide an excerpt or rough account and state which assumptions remain. Ask only for missing context that changes the advice.
Have a first useful conversation
Use the supported lens to help me examine the challenge. Offer an observation that changes how I see it, ask a focused question and respond to my answer. Give me room to develop the idea. Be willing to disagree, notice a tension or identify an assumption; do not turn the admired person into a machine for praising me.
Keep the source-based principle, your application to my situation and any unsupported possibility distinguishable. Where the historical lens does not fit current facts or the person’s experience does not cover the issue, say so briefly and use current evidence or ordinary reasoning explicitly. When the conversation reaches a useful point, propose concrete actions or a small test: what I would do, what I expect to learn and what result would change my mind. Wait for my decision before treating an action as agreed. Draft a relevant practical aid, such as a conversation opening or experiment brief, when it helps.
Ask whether the interaction has the qualities I wanted—its helpfulness, directness and distinctive perspective—and adjust the setup from my response. Judge the trial by what it helps me see or do, not by whether it sounds like an impersonation.
Make it a buddy I can return to
Inspect the actual environment’s support for saved instructions, persistent chats, projects, files or memory before promising continuity. Use the available permitted route to prepare the reusable setup: its purpose, source-based lens, source links, interaction preferences and the conversation method above. If configuration requires my action, give the exact setup text and the smallest necessary steps.
Maintain a concise, editable continuity note with the current challenge, context I have confirmed, useful questions, ideas considered, decisions I actually made, agreed tests, observed results and the next open thread. Keep your proposals separate from my decisions. Save it only in an agreed available location; otherwise give me a portable copy to bring back. Do not claim automatic memory or proactive check-ins that have not been configured and verified.
At the end of this first session, give me the reusable buddy instructions, sources, updated continuity note and any agreed practical aid. Show the simplest way to resume. In later sessions, load or ask for the note, establish what happened since last time, update relevant evidence and check for newer methods or tool capabilities when they could improve the conversation. Help me revise the advice when reality disagrees with it.
Done when
You have tried a useful conversation with a simulated adviser of your choice and have reusable instructions, source references and a continuity note for returning to it. You know what perspective it draws on and can keep improving the approach as your needs, available methods and evidence change.
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.