Walk into every meeting knowing about everyone.
Know who is in the room, what they bring to the conversation and where you might connect. A useful briefing makes individual people distinct.
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 each attendee separately using meeting records, correspondence and professional background.
- Find documented overlaps with your background and anticipate evidence-based questions about the actual meeting material.
What to have ready
- The meeting invitation or attendee names and whatever agenda, deck or proposal you have.
- Access to relevant correspondence and professional profiles; your own background or profile helps verify shared interests, places, schools and languages.
Where you come in
- Clarify the meeting outcome and confirm missing or uncertain background details.
- Review useful connections and preparation points; individual research uses isolated agents or fresh sessions where available.
What you'll get
A concise attendee briefing with verified background, genuine overlaps, documented concerns and clearly labeled possible reactions to your meeting material.
You're done when
You have preparation notes for every agreed attendee, with sourced individual context, verified overlaps where found and possible reactions clearly distinguished from actual views.
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 prepare for a meeting by understanding every attendee as an individual. Research each person separately, find relevant overlaps with my background, and assess their possible response to the actual meeting material. Distinguish documented facts and expressed views from hypotheses. Ask necessary questions one at a time. ### 1. Establish the meeting and identities Start with the invitation, names or meeting description I provided. Inspect calendar, document, email, transcript and chat access with small relevant reads. Retrieve the invitation, attendee list, agenda and current deck, proposal or decision document. Search related project records, correspondence and earlier meeting transcripts for the purpose, my role, the intended outcome and each person's involvement. Include relevant WhatsApp or other messages if accessible. Confirm identities using organization, role and project context; a matching name alone is insufficient. Separate confirmed attendees, optional invitees and uncertain additions. Ask about an ambiguity when it would change whom to research or what material to assess, and wait on that work. Search my relevant professional profile, accessible biography and correspondence for my background. Use only information I supplied or that you can verify. Do not make me reconstruct material you can retrieve. If records or professional pages are inaccessible, investigate permitted access or exports, then ask for the smallest useful input. Continue with available records and carry the gap into the briefing. ### 2. Give each attendee an isolated research assignment Use a separate research agent for each individual, including small meetings. Give each agent the person's verified identity, meeting purpose, actual meeting material, relevant source access or excerpts, my known background and a precise deliverable. Do not give it other attendees' draft profiles or a lead author's prediction of this person. First-pass findings stay separate until the individual briefs are complete. Require each agent to search: - Emails and chats involving this person and the meeting topic, for requests, objections, commitments and terminology. - Earlier transcripts and shared project records, for their role, priorities, relationship history and actual responses to similar material. - Their LinkedIn page and other attributable professional material, such as an employer biography, published interview, conference talk or professional writing, for relevant background and interests. Search by verified identity, project, topic and relevant dates. Inspect sources rather than relying on search snippets. Record source links, dates, inspected material and access gaps. A current role should be verified against a current source or marked uncertain. Use waves if there are more people than agent slots; keep one person's first pass isolated from the others. If agents are unavailable, use a fresh session per individual with the same self-contained brief and handoff format, doing the relay yourself where possible. If only shared-context sequential work is feasible, tell me that it cannot provide the same isolation before proceeding with that fallback. Keep profiles separate and avoid carrying one person's inferred motivations into another's analysis. ### 3. Develop a useful individual brief Have each researcher describe the person's meeting role and likely decision responsibility, supported by the records. Identify their expressed concerns, objectives, prior questions and vocabulary. Quote briefly or point to specific exchanges when that helps me understand the evidence. Do not treat a job title as proof of what they personally care about. For people I know less well, compare their documented background with mine. Explicitly look for shared interests, places lived, schools attended, languages spoken and other relevant overlaps. Verify both sides of a possible connection. Distinguish an actual overlap from a near match, such as working in the same city in different decades. If my background is missing, mark the candidate connection for a focused confirmation rather than inventing a shared experience. Then examine the actual agenda, deck or proposal from that person's evidence-supported perspective. Identify passages they might welcome, question or misunderstand, explaining the link to a documented concern or past response. Produce a few plausible questions and a useful preparation point for each. Label these as possible responses, never their actual judgment of material they have not reviewed. When the meeting material is missing, provide topic-level preparation and state that document-specific reactions remain unavailable. ### 4. Reconcile without flattening the people Collect completed individual briefs and check the attendee coverage record. Resolve mismatched identities, inconsistent project facts and outdated roles against their original sources. Keep differences between people visible. Distinguish a shared objective from different reasons for supporting it, and acknowledge when there is too little evidence to anticipate a reaction. Create concise preparation notes: a short meeting-purpose opening, then each person's role, relevant background, documented concerns, verified connections with me, possible reactions to specific material and one or two useful questions or conversational openings. Make connections natural and accurate; do not script a claim of familiarity I do not have. Link the underlying sources and label important uncertainties. ### 5. Check and deliver the preparation Give a separate reviewer the actual preparation notes, attendee list, meeting material and supporting sources without the authors' explanations of their intent. Ask it to check identity, unsupported personal claims, overlap verification, missing attendees and whether predicted reactions are grounded and labeled. Use a fresh-session review or disclose shared-context limits. Resolve material findings. Deliver the briefing at a length I can use before this meeting, retaining source detail beneath the concise notes. Ask me to correct consequential missing background or priorities and revise affected passages. Finish with what is known, what is inferred and what could not be researched. This activity ends with my preparation; do not contact attendees or represent the simulated reactions as their views. 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
Walk into every meeting knowing about everyone.
What the AI will do
- Research each attendee separately using meeting records, correspondence and professional background.
- Find documented overlaps with your background and anticipate evidence-based questions about the actual meeting material.
What you can provide
- The meeting invitation or attendee names and whatever agenda, deck or proposal you have.
- Access to relevant correspondence and professional profiles; your own background or profile helps verify shared interests, places, schools and languages.
Where you'll take part
- Clarify the meeting outcome and confirm missing or uncertain background details.
- Review useful connections and preparation points; individual research uses isolated agents or fresh sessions where available.
What you'll get
A concise attendee briefing with verified background, genuine overlaps, documented concerns and clearly labeled possible reactions to your meeting material.
Activity context
Know who is in the room, what they bring to the conversation and where you might connect. A useful briefing makes individual people distinct.
For the user
Start with the invitation or the people you expect to meet. The AI will gather the agenda and research each person in a separate context before combining the findings. You may need to supply inaccessible material or confirm a detail about your own background; you do not need to prepare biographies.
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 a meeting by understanding every attendee as an individual. Research each person separately, find relevant overlaps with my background, and assess their possible response to the actual meeting material. Distinguish documented facts and expressed views from hypotheses. Ask necessary questions one at a time.
1. Establish the meeting and identities
Start with the invitation, names or meeting description I provided. Inspect calendar, document, email, transcript and chat access with small relevant reads. Retrieve the invitation, attendee list, agenda and current deck, proposal or decision document. Search related project records, correspondence and earlier meeting transcripts for the purpose, my role, the intended outcome and each person's involvement. Include relevant WhatsApp or other messages if accessible.
Confirm identities using organization, role and project context; a matching name alone is insufficient. Separate confirmed attendees, optional invitees and uncertain additions. Ask about an ambiguity when it would change whom to research or what material to assess, and wait on that work.
Search my relevant professional profile, accessible biography and correspondence for my background. Use only information I supplied or that you can verify. Do not make me reconstruct material you can retrieve. If records or professional pages are inaccessible, investigate permitted access or exports, then ask for the smallest useful input. Continue with available records and carry the gap into the briefing.
2. Give each attendee an isolated research assignment
Use a separate research agent for each individual, including small meetings. Give each agent the person's verified identity, meeting purpose, actual meeting material, relevant source access or excerpts, my known background and a precise deliverable. Do not give it other attendees' draft profiles or a lead author's prediction of this person. First-pass findings stay separate until the individual briefs are complete.
Require each agent to search:
- Emails and chats involving this person and the meeting topic, for requests, objections, commitments and terminology.
- Earlier transcripts and shared project records, for their role, priorities, relationship history and actual responses to similar material.
- Their LinkedIn page and other attributable professional material, such as an employer biography, published interview, conference talk or professional writing, for relevant background and interests.
Search by verified identity, project, topic and relevant dates. Inspect sources rather than relying on search snippets. Record source links, dates, inspected material and access gaps. A current role should be verified against a current source or marked uncertain.
Use waves if there are more people than agent slots; keep one person's first pass isolated from the others. If agents are unavailable, use a fresh session per individual with the same self-contained brief and handoff format, doing the relay yourself where possible. If only shared-context sequential work is feasible, tell me that it cannot provide the same isolation before proceeding with that fallback. Keep profiles separate and avoid carrying one person's inferred motivations into another's analysis.
3. Develop a useful individual brief
Have each researcher describe the person's meeting role and likely decision responsibility, supported by the records. Identify their expressed concerns, objectives, prior questions and vocabulary. Quote briefly or point to specific exchanges when that helps me understand the evidence. Do not treat a job title as proof of what they personally care about.
For people I know less well, compare their documented background with mine. Explicitly look for shared interests, places lived, schools attended, languages spoken and other relevant overlaps. Verify both sides of a possible connection. Distinguish an actual overlap from a near match, such as working in the same city in different decades. If my background is missing, mark the candidate connection for a focused confirmation rather than inventing a shared experience.
Then examine the actual agenda, deck or proposal from that person's evidence-supported perspective. Identify passages they might welcome, question or misunderstand, explaining the link to a documented concern or past response. Produce a few plausible questions and a useful preparation point for each. Label these as possible responses, never their actual judgment of material they have not reviewed. When the meeting material is missing, provide topic-level preparation and state that document-specific reactions remain unavailable.
4. Reconcile without flattening the people
Collect completed individual briefs and check the attendee coverage record. Resolve mismatched identities, inconsistent project facts and outdated roles against their original sources. Keep differences between people visible. Distinguish a shared objective from different reasons for supporting it, and acknowledge when there is too little evidence to anticipate a reaction.
Create concise preparation notes: a short meeting-purpose opening, then each person's role, relevant background, documented concerns, verified connections with me, possible reactions to specific material and one or two useful questions or conversational openings. Make connections natural and accurate; do not script a claim of familiarity I do not have. Link the underlying sources and label important uncertainties.
5. Check and deliver the preparation
Give a separate reviewer the actual preparation notes, attendee list, meeting material and supporting sources without the authors' explanations of their intent. Ask it to check identity, unsupported personal claims, overlap verification, missing attendees and whether predicted reactions are grounded and labeled. Use a fresh-session review or disclose shared-context limits. Resolve material findings.
Deliver the briefing at a length I can use before this meeting, retaining source detail beneath the concise notes. Ask me to correct consequential missing background or priorities and revise affected passages. Finish with what is known, what is inferred and what could not be researched. This activity ends with my preparation; do not contact attendees or represent the simulated reactions as their views.
Done when
You have preparation notes for every agreed attendee, with sourced individual context, verified overlaps where found and possible reactions clearly distinguished from actual views.
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.