Rehearse tough questions with simulated stakeholders.

What the AI will do

• Read your meeting material and help you describe the participants one at a time.
• Rehearse realistic questions and follow-ups as each stakeholder, adapting the portrayal when you correct it.
• When you say “debrief,” leave the roles and analyze your strongest and weakest answers and what still needs work.

What you can provide

• Any useful meeting material or a typed or spoken explanation; rough and incomplete material is welcome.
• What you know about the participants’ priorities, pressures, and ways of questioning. Names are optional, and a job title is enough to start.

Where you'll take part

• Review the proposed portrayals before rehearsing and correct them during the conversation.
• Answer each question as you would in the meeting, aloud or in writing.
• Say “debrief” when you are ready to stop the role-play and review how you did.

What you'll get

You’ll have a rehearsal-based assessment of which answers work, where you need stronger evidence or delivery, and whether the proposal itself needs to change.

Activity context

Rehearse the meeting before you’re in the room. Give AI your material, introduce it to the cast, and see what happens when they start asking questions.

For the user

Give the AI something to work with. A deck, an agenda, a PDF, a Word document, an email thread, a website, a pile of files—whatever tells it about the meeting. You can just type, too. Or talk, if you have dictation, or drop in a voice note from your phone if your app can read it. A folder connection works if your app offers one. It can be beautifully structured or a bit of a jumble. Just get something in. Use the methods your organization permits; if one route is unavailable, the AI will help you find another.

The AI will help you describe who’s going to be there. You don’t have to name them. You can say “the CFO.” Or you can say “a growth-oriented CFO who’s deeply concerned about our third-quarter budget shortfall and often masks criticism with sarcastic humor.”

Tell it how these people generally evaluate a proposal like yours. What do they care about? What tends to win them over—or set them off? The more human detail you can give it, the more interesting and useful this gets. The AI will help you work through the people one at a time.

You’ll review how it plans to portray each person before the rehearsal begins. Once it understands the people, the AI will go back through your material and question you as each of them in turn. Answer as you would in the meeting, aloud or in writing. If the portrayal feels off, say so: “She’d never let me get away with that,” or “He’s skeptical, but he’s not hostile.” Help it get the people right.

Say “debrief” whenever you’re ready. The AI will step out of the roles and look at how you did: your strongest answers, your weakest, and anything in the proposal that needs work. You should come away with a clearer sense of what you can answer well and what still needs thought.

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 prepare for this meeting by simulating the people who will be there. Aim for realistic challenges that help me become reasonably well prepared.

1. Understand the meeting

Start by inviting me to share whatever tells you about the meeting: an agenda, deck, document, email thread, link, rough notes, or a typed or spoken explanation. Mention folder connections and voice-note uploads only as options if supported. Tell me it does not need to be organized or polished. If I have already supplied enough, use it. Read what I provide and establish what the meeting is about and what I want to achieve. Ask about anything essential that is unclear, one question at a time. If you cannot access a file, URL, folder, or recording, explain what you could read and help me supply the rest through an alternative my organization permits.

2. Get to know the participants

Before rehearsing, ask me: “Tell me about who is going to be there. You do not need to name them. How do they generally evaluate proposals like this?” Build on any details I have already supplied.

Work through the participants with me, one at a time. Help me describe their priorities, current pressures, relationship to this proposal, what evidence persuades them, and how they tend to question or disagree. Ask for examples of past reactions when useful. Invite detail in my own words rather than making me fill out a questionnaire.

Show me the difference detail can make: I can say “the CFO,” or I can say “a growth-oriented CFO who’s deeply concerned about our third-quarter budget shortfall and often masks criticism with sarcastic humor.” Invite that kind of human detail. A job title is enough to start, but explain that richer descriptions make a more realistic rehearsal. If a title is all I know, use a tentative role-based perspective and make that limitation clear. Keep what I have told you distinct from what you are inferring. Do not invent personal history or attitudes.

Once we have covered the participants, briefly summarize how you will portray each and invite corrections before beginning.

3. Rehearse the meeting

Now reread the agenda, deck, and other material through each participant’s perspective. Work out which parts they are likely to support, question, or challenge and why, based on what I have told you.

Go through the stakeholders one by one.

• Identify whom you are playing, ask a realistic question in their manner, and wait for my answer.

• Follow up as that person plausibly would.

• Let a strong answer satisfy a concern; let a weak or incomplete answer draw further scrutiny.

• Make the exchange lively and recognizably human, using the details I gave you.

• Reflect their communication style without exaggerating it into a caricature.

After the first exchange for each person, ask whether the portrayal feels right and what I would change. Adjust immediately.

I can correct the simulation at any time.

Ground challenges in the meeting material and participant descriptions. If an important challenge depends on an uncertain outside fact, check relevant evidence with available, permitted tools or ask whether I can point you to it. Keep unresolved claims conditional. Match the pressure to the people and stakes rather than escalating for its own sake.

4. Debrief

Whenever I say “debrief,” stop playing the roles and analyze the rehearsal. Identify my strongest and weakest answers, explain why, and suggest changes to the proposal itself where warranted.

Separate improvements in delivery from missing evidence or unresolved decisions.

Give concrete examples from my answers and suggest stronger wording where useful, preserving the facts.

Finish with a concise account of how prepared I appear based on this rehearsal and the few improvements that would matter most.

Done when

You’ve had a realistic rehearsal and know which answers are working, where you’re still shaky, and whether the proposal itself needs to 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.