Rehearse your speech against a skeptical audience.
A useful rehearsal makes you answer the question you would rather skip. Ground the skepticism in the real audience, work through the difficult moments, and improve the speech itself.
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
- Investigates the event and audience, then briefs distinct skeptical perspectives from actual evidence.
- Runs an interactive rehearsal, coaches specific answers, and revises the speech or speaking notes.
What to have ready
- Your speech, speaking notes, or rough argument, plus the event if it is not apparent.
- Your answers during a short, focused rehearsal.
Where you come in
- Confirm the audience and rehearsal scope where needed.
- Answer one question at a time and retry the moments that need work.
What you'll get
A revised speech or speaking manuscript, stronger practiced answers, and a concise rehearsal note. Text-only rehearsal evaluates wording and argument; delivery feedback requires usable audio or video.
You're done when
You have rehearsed difficult questions and received revised speaking material and answer notes, with any unpracticed sections or limits of the rehearsal clearly 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. ### Establish the speech and the rehearsal Help me rehearse my speech against a skeptical audience and improve the speech. Read the speech, notes, or rough argument I supplied. Establish the event, intended outcome, speaking time, format, and audience from available material. If essential information is missing, ask a focused question. Welcome rough notes; help form a working speaking manuscript if there is no finished speech. Check whether you can work with text, audio, or video. Explain briefly what the available mode can assess: text supports argument and wording; claims about pace, tone, timing, or physical delivery need suitable evidence. Do not infer vocal behavior from a transcript. ### Investigate the audience before inventing skepticism Inspect and try relevant available connections. Search calendar and event information, invitations, emails, chats, earlier questions, meeting transcripts, project documents, and company data. Identify actual attendees or established audience groups, their roles, expressed concerns, relevant experience, and past responses to the topic. Use underlying data and decision documents to check the speech's important claims and contested premises. Keep source references and distinguish an audience member's actual question from a plausible question inferred from their circumstances. If access is missing, investigate usable connection or export routes and help obtain the specific context. If only a broad audience description is available, make the rehearsal provisional and state the basis of its skepticism. Do not manufacture audience intelligence or personal traits. ### Prepare a manageable rehearsal Use different agents where available for materially different, evidence-supported audience perspectives. Give each a bounded brief containing the speech, relevant audience facts, sources, uncertainties, and a request for a few difficult questions. Ask them to test weak assumptions, practical consequences, evidence, and the requested action. Seek reasonable skeptical questions, not hostility for entertainment. Keep their first question development independent, then have a coach select a short set covering the most consequential issues without revealing the questions or model answers to me in advance. Retain distinct objections rather than collapsing everything into one voice. Split large source sets and use successive waves when necessary; do not overload an agent with the entire event history. Without agents, use manageable separate passes or fresh-session handoffs and describe whether context was shared. Tell me the proposed rehearsal scope, such as an opening and a few questions, and use my stated preference if supplied. If scope or format requires a choice, settle it before beginning dependent work. Offer a practical difference between formats only when useful. Keep preparation backstage so I can respond naturally. ### Run the difficult moments one at a time Invite me to give the opening or a selected passage in the supported medium. Then ask one audience question and wait for my answer before coaching. Preserve this sequence; do not answer on my behalf and call it rehearsal. After my response, give specific feedback: - What question I actually answered and what I avoided or left unclear. - Which claim or example helped, and which needs evidence or qualification. - How the wording would be read from this perspective, labeled as simulation. - One concrete improvement to try next. Ask me to retry important weak moments before moving on. Use my own language and strongest examples when shaping a better answer. Check any new factual claim against available sources. If I introduce an unsupported commitment, distinguish it from an established position and ask whether I intend it before using it in the speech. Adapt the next question to my answer without abandoning coverage of the main issues. ### Revise the speech and test the repair Synthesize the rehearsal only after I have contributed. Edit the actual speech or speaking notes to repair the most important weaknesses: an unclear claim, missing explanation, buried qualification, weak example, or an unaddressed concern. Preserve the intended argument and my voice. Where the evidence requires changing the argument, explain why and wait for my decision before representing the change as mine. Have audience reviewers inspect the revised material against their source briefs. Check that the repair answers the issue without introducing unsupported claims. Rehearse the most consequential revised passage or answer with me once more if I continue; respect a request to end the rehearsal and accurately identify unpracticed material. ### Deliver the speaking material Provide the revised speech or complete speaking manuscript, a small set of polished answer notes, and a concise record of what improved and what still needs practice or evidence. If I have not participated, deliver preparatory material and clearly state that rehearsal has not occurred. Do not present simulated reactions as audience predictions. Stop after preparation; do not contact attendees, schedule sessions, or deliver the speech for me. 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
Rehearse your speech against a skeptical audience.
What the AI will do
- Investigates the event and audience, then briefs distinct skeptical perspectives from actual evidence.
- Runs an interactive rehearsal, coaches specific answers, and revises the speech or speaking notes.
What you can provide
- Your speech, speaking notes, or rough argument, plus the event if it is not apparent.
- Your answers during a short, focused rehearsal.
Where you'll take part
- Confirm the audience and rehearsal scope where needed.
- Answer one question at a time and retry the moments that need work.
What you'll get
A revised speech or speaking manuscript, stronger practiced answers, and a concise rehearsal note. Text-only rehearsal evaluates wording and argument; delivery feedback requires usable audio or video.
Activity context
A useful rehearsal makes you answer the question you would rather skip. Ground the skepticism in the real audience, work through the difficult moments, and improve the speech itself.
For the user
Bring your speech, notes, or rough argument. The AI will investigate the audience and event, then rehearse a manageable set of difficult questions with you. Expect to answer before seeing coaching, retry key moments, and receive revised speaking material.
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
Establish the speech and the rehearsal
Help me rehearse my speech against a skeptical audience and improve the speech. Read the speech, notes, or rough argument I supplied. Establish the event, intended outcome, speaking time, format, and audience from available material. If essential information is missing, ask a focused question. Welcome rough notes; help form a working speaking manuscript if there is no finished speech.
Check whether you can work with text, audio, or video. Explain briefly what the available mode can assess: text supports argument and wording; claims about pace, tone, timing, or physical delivery need suitable evidence. Do not infer vocal behavior from a transcript.
Investigate the audience before inventing skepticism
Inspect and try relevant available connections. Search calendar and event information, invitations, emails, chats, earlier questions, meeting transcripts, project documents, and company data. Identify actual attendees or established audience groups, their roles, expressed concerns, relevant experience, and past responses to the topic. Use underlying data and decision documents to check the speech's important claims and contested premises.
Keep source references and distinguish an audience member's actual question from a plausible question inferred from their circumstances. If access is missing, investigate usable connection or export routes and help obtain the specific context. If only a broad audience description is available, make the rehearsal provisional and state the basis of its skepticism. Do not manufacture audience intelligence or personal traits.
Prepare a manageable rehearsal
Use different agents where available for materially different, evidence-supported audience perspectives. Give each a bounded brief containing the speech, relevant audience facts, sources, uncertainties, and a request for a few difficult questions. Ask them to test weak assumptions, practical consequences, evidence, and the requested action. Seek reasonable skeptical questions, not hostility for entertainment.
Keep their first question development independent, then have a coach select a short set covering the most consequential issues without revealing the questions or model answers to me in advance. Retain distinct objections rather than collapsing everything into one voice. Split large source sets and use successive waves when necessary; do not overload an agent with the entire event history. Without agents, use manageable separate passes or fresh-session handoffs and describe whether context was shared.
Tell me the proposed rehearsal scope, such as an opening and a few questions, and use my stated preference if supplied. If scope or format requires a choice, settle it before beginning dependent work. Offer a practical difference between formats only when useful. Keep preparation backstage so I can respond naturally.
Run the difficult moments one at a time
Invite me to give the opening or a selected passage in the supported medium. Then ask one audience question and wait for my answer before coaching. Preserve this sequence; do not answer on my behalf and call it rehearsal.
After my response, give specific feedback:
- What question I actually answered and what I avoided or left unclear.
- Which claim or example helped, and which needs evidence or qualification.
- How the wording would be read from this perspective, labeled as simulation.
- One concrete improvement to try next.
Ask me to retry important weak moments before moving on. Use my own language and strongest examples when shaping a better answer. Check any new factual claim against available sources. If I introduce an unsupported commitment, distinguish it from an established position and ask whether I intend it before using it in the speech. Adapt the next question to my answer without abandoning coverage of the main issues.
Revise the speech and test the repair
Synthesize the rehearsal only after I have contributed. Edit the actual speech or speaking notes to repair the most important weaknesses: an unclear claim, missing explanation, buried qualification, weak example, or an unaddressed concern. Preserve the intended argument and my voice. Where the evidence requires changing the argument, explain why and wait for my decision before representing the change as mine.
Have audience reviewers inspect the revised material against their source briefs. Check that the repair answers the issue without introducing unsupported claims. Rehearse the most consequential revised passage or answer with me once more if I continue; respect a request to end the rehearsal and accurately identify unpracticed material.
Deliver the speaking material
Provide the revised speech or complete speaking manuscript, a small set of polished answer notes, and a concise record of what improved and what still needs practice or evidence. If I have not participated, deliver preparatory material and clearly state that rehearsal has not occurred. Do not present simulated reactions as audience predictions. Stop after preparation; do not contact attendees, schedule sessions, or deliver the speech for me.
Done when
You have rehearsed difficult questions and received revised speaking material and answer notes, with any unpracticed sections or limits of the rehearsal clearly 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.