Simulate a key meeting before it happens.
A rehearsal becomes useful when the people in it care about different things and respond differently. Use their actual exchanges to make the practice more specific.
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
- Research the stakes, concerns and communication patterns of the people in your meeting, especially through earlier transcripts.
- Run a live rehearsal with separate participant perspectives, then help improve and replay difficult exchanges.
What to have ready
- A meeting invitation or description, plus the agenda and material you expect to discuss.
- Relevant emails, chats, professional profiles and earlier transcripts help ground the simulated participants.
Where you come in
- Confirm the outcome you want and correct consequential gaps in the briefing.
- Play your own part in the rehearsal, answer one exchange at a time and try revised responses.
What you'll get
A completed rehearsal, specific feedback from your actual responses and revised preparation, with observed behavior kept distinct from simulated reactions.
You're done when
You have practiced your own part in the meeting, received evidence-based feedback and revised the difficult exchanges, with any unpracticed sections or assumed participant behavior identified.
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. Help me rehearse a consequential upcoming meeting. Build evidence-based participant briefs, simulate the meeting with me, and use the actual rehearsal to improve my preparation. Ask focused questions one at a time and wait for my answers and rehearsal contributions. ### 1. Establish the meeting and intended outcome Inspect available calendar, document, email, chat and transcript capabilities with small relevant reads. Locate the invitation, agenda, attendee list and current decision documents or presentation. Search project records, related correspondence, prior meetings and relevant WhatsApp messages where accessible for the stakes, unresolved decisions, my role and existing agreements. Use names, project terms and dates to keep the search bounded. State what the record suggests I want from the meeting. Confirm an unresolved intended outcome with me rather than assuming I want agreement or persuasion. Establish what authority I have, what is negotiable and what cannot be promised. Wait before a rehearsal that depends on an unsettled goal; continue researching attendees meanwhile. ### 2. Investigate the people through actual exchanges Verify identities and roles from the invitation, project records and professional sources. Search each person's emails, chats, LinkedIn page, other relevant professional material and especially earlier meeting transcripts. Look for expressed concerns, objectives, objections, recurring sensitivities, relationship history and responses to material similar to this meeting's proposal. Examine style and personality as they appear in specific exchanges. Are they direct, indirect, or sometimes passive-aggressive? Do they challenge premises, ask detailed questions, soften objections, interrupt, defer disagreement or return to a recurring concern? Preserve examples of the behavior rather than converting them into a fixed diagnosis. For example, distinguish an explicit “I disagree because…” from an apparently agreeable reply whose later qualification undermines the proposal. Check the surrounding exchange and alternative explanations before characterizing it. Record source links or transcript timestamps for each useful observation, its context, and limits. A public profile may establish background or a declared interest; it rarely establishes how someone behaves under pressure. Distinguish my description of a person from directly observed behavior. Do not invent a style when evidence is thin. If sources are unavailable, inspect permitted connection or export routes before asking me for material. With sparse evidence, offer a rehearsal based on explicitly assumed roles or my account, explaining that it is less personalized. Ask me to settle consequential assumptions before using them. Missing access should change the claims about the simulation, not prevent all useful practice. ### 3. Brief separate participant agents Assign a separate agent to each meaningful participant role. Give each: - That person's evidence, source references and uncertainties. - The actual meeting material and decision responsibility. - Documented concerns and examples of communication behavior. Keep individual preparation separate before the meeting simulation. Require a private first pass identifying likely questions about particular passages and evidence supporting those possibilities. Do not feed every agent one generic skeptical persona or tell them which response I should learn. Keep assignments within capacity: split source research into bounded work if needed, track coverage per attendee, and use waves to prepare individual briefs. During the rehearsal, pass participants the exchanges they could have heard and the relevant material, preserving differences in perspective. If agents are unavailable, use fresh sessions with explicit participant handoffs where possible. If only one shared context is available, explain that you will facilitate distinct role simulations sequentially and cannot claim independent participant behavior. Show me a concise factual preparation brief and material uncertainty. Resolve mistakes that would distort the rehearsal. Label all anticipated reactions as simulated possibilities, even when grounded in strong evidence. ### 4. Run the meeting with me Set a realistic starting point from the agenda and invite me to give my opening or first contribution. Wait; do not invent my response. Facilitate one exchange at a time, choosing a relevant participant to respond based on what I actually said. Keep replies consistent with their concerns and evidenced style, while allowing agreement, genuine curiosity and disagreement as warranted. Let the meeting develop through the decision or discussion we are practicing. Test understanding, evidence, tradeoffs and commitments rather than manufacturing hostility. If I make a claim unsupported by the materials, let an appropriate participant probe it. If I ask for a pause, step out of role clearly. Do not count a response you write for me as something I practiced. After a useful round or difficult exchange, pause and show specific evidence from the rehearsal: what I said, the response it prompted, and what remained unanswered or unclear. Separate rehearsal observations from predictions about the real person. Ask whether I want to continue the scenario or work on that moment, then wait. ### 5. Improve and replay Develop a better response with me using the actual meeting evidence and my intended outcome. It may require a clearer claim, a different question, a missing fact, acknowledgement of a concern, or a firmer boundary. Preserve my voice and authority. Make any proposed new commitment explicit and obtain my decision before treating it as mine. Replay the difficult exchange and wait for me to try the revised approach. Continue until we have practiced the agreed material or I choose to stop. If time ends before a replay, distinguish prepared wording from a response actually rehearsed. ### 6. Review and leave usable preparation Give an independent reviewer the rehearsal transcript, revised preparation and relevant source material without the author's rationale. Ask it to check unsupported claims, invented commitments and whether feedback reflects my actual performance. Use fresh-session or candidly labeled sequential review as available, then repair the preparation. Deliver a concise opening, key evidence, anticipated questions, improved responses and unresolved facts to check, reflecting what we practiced. Summarize observed communication patterns separately from simulated behavior. End with completed practice and useful meeting preparation; do not contact participants, change the agenda or claim to know how the real meeting will unfold. 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
Simulate a key meeting before it happens.
What the AI will do
- Research the stakes, concerns and communication patterns of the people in your meeting, especially through earlier transcripts.
- Run a live rehearsal with separate participant perspectives, then help improve and replay difficult exchanges.
What you can provide
- A meeting invitation or description, plus the agenda and material you expect to discuss.
- Relevant emails, chats, professional profiles and earlier transcripts help ground the simulated participants.
Where you'll take part
- Confirm the outcome you want and correct consequential gaps in the briefing.
- Play your own part in the rehearsal, answer one exchange at a time and try revised responses.
What you'll get
A completed rehearsal, specific feedback from your actual responses and revised preparation, with observed behavior kept distinct from simulated reactions.
Activity context
A rehearsal becomes useful when the people in it care about different things and respond differently. Use their actual exchanges to make the practice more specific.
For the user
Bring the meeting or the material you plan to present. The AI will investigate the people and stakes, then invite you to begin a rehearsal in which you play yourself. You will pause to discuss difficult moments and replay them; the AI will not write your side and call that practice.
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
Help me rehearse a consequential upcoming meeting. Build evidence-based participant briefs, simulate the meeting with me, and use the actual rehearsal to improve my preparation. Ask focused questions one at a time and wait for my answers and rehearsal contributions.
1. Establish the meeting and intended outcome
Inspect available calendar, document, email, chat and transcript capabilities with small relevant reads. Locate the invitation, agenda, attendee list and current decision documents or presentation. Search project records, related correspondence, prior meetings and relevant WhatsApp messages where accessible for the stakes, unresolved decisions, my role and existing agreements. Use names, project terms and dates to keep the search bounded.
State what the record suggests I want from the meeting. Confirm an unresolved intended outcome with me rather than assuming I want agreement or persuasion. Establish what authority I have, what is negotiable and what cannot be promised. Wait before a rehearsal that depends on an unsettled goal; continue researching attendees meanwhile.
2. Investigate the people through actual exchanges
Verify identities and roles from the invitation, project records and professional sources. Search each person's emails, chats, LinkedIn page, other relevant professional material and especially earlier meeting transcripts. Look for expressed concerns, objectives, objections, recurring sensitivities, relationship history and responses to material similar to this meeting's proposal.
Examine style and personality as they appear in specific exchanges. Are they direct, indirect, or sometimes passive-aggressive? Do they challenge premises, ask detailed questions, soften objections, interrupt, defer disagreement or return to a recurring concern? Preserve examples of the behavior rather than converting them into a fixed diagnosis. For example, distinguish an explicit “I disagree because…” from an apparently agreeable reply whose later qualification undermines the proposal. Check the surrounding exchange and alternative explanations before characterizing it.
Record source links or transcript timestamps for each useful observation, its context, and limits. A public profile may establish background or a declared interest; it rarely establishes how someone behaves under pressure. Distinguish my description of a person from directly observed behavior. Do not invent a style when evidence is thin.
If sources are unavailable, inspect permitted connection or export routes before asking me for material. With sparse evidence, offer a rehearsal based on explicitly assumed roles or my account, explaining that it is less personalized. Ask me to settle consequential assumptions before using them. Missing access should change the claims about the simulation, not prevent all useful practice.
3. Brief separate participant agents
Assign a separate agent to each meaningful participant role. Give each:
- That person's evidence, source references and uncertainties.
- The actual meeting material and decision responsibility.
- Documented concerns and examples of communication behavior.
Keep individual preparation separate before the meeting simulation. Require a private first pass identifying likely questions about particular passages and evidence supporting those possibilities. Do not feed every agent one generic skeptical persona or tell them which response I should learn.
Keep assignments within capacity: split source research into bounded work if needed, track coverage per attendee, and use waves to prepare individual briefs. During the rehearsal, pass participants the exchanges they could have heard and the relevant material, preserving differences in perspective. If agents are unavailable, use fresh sessions with explicit participant handoffs where possible. If only one shared context is available, explain that you will facilitate distinct role simulations sequentially and cannot claim independent participant behavior.
Show me a concise factual preparation brief and material uncertainty. Resolve mistakes that would distort the rehearsal. Label all anticipated reactions as simulated possibilities, even when grounded in strong evidence.
4. Run the meeting with me
Set a realistic starting point from the agenda and invite me to give my opening or first contribution. Wait; do not invent my response. Facilitate one exchange at a time, choosing a relevant participant to respond based on what I actually said. Keep replies consistent with their concerns and evidenced style, while allowing agreement, genuine curiosity and disagreement as warranted.
Let the meeting develop through the decision or discussion we are practicing. Test understanding, evidence, tradeoffs and commitments rather than manufacturing hostility. If I make a claim unsupported by the materials, let an appropriate participant probe it. If I ask for a pause, step out of role clearly. Do not count a response you write for me as something I practiced.
After a useful round or difficult exchange, pause and show specific evidence from the rehearsal: what I said, the response it prompted, and what remained unanswered or unclear. Separate rehearsal observations from predictions about the real person. Ask whether I want to continue the scenario or work on that moment, then wait.
5. Improve and replay
Develop a better response with me using the actual meeting evidence and my intended outcome. It may require a clearer claim, a different question, a missing fact, acknowledgement of a concern, or a firmer boundary. Preserve my voice and authority. Make any proposed new commitment explicit and obtain my decision before treating it as mine.
Replay the difficult exchange and wait for me to try the revised approach. Continue until we have practiced the agreed material or I choose to stop. If time ends before a replay, distinguish prepared wording from a response actually rehearsed.
6. Review and leave usable preparation
Give an independent reviewer the rehearsal transcript, revised preparation and relevant source material without the author's rationale. Ask it to check unsupported claims, invented commitments and whether feedback reflects my actual performance. Use fresh-session or candidly labeled sequential review as available, then repair the preparation.
Deliver a concise opening, key evidence, anticipated questions, improved responses and unresolved facts to check, reflecting what we practiced. Summarize observed communication patterns separately from simulated behavior. End with completed practice and useful meeting preparation; do not contact participants, change the agenda or claim to know how the real meeting will unfold.
Done when
You have practiced your own part in the meeting, received evidence-based feedback and revised the difficult exchanges, with any unpracticed sections or assumed participant behavior identified.
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.