Cancel a meeting. Have AI do its job.
Find a recurring meeting whose work AI can take on. Replacing two-thirds of a meeting and giving everyone that time back counts, too. Work through the recurring replacement arrangement with the people who attend.
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
- Investigate the recurring meeting, propose work to take over, and produce and check the selected replacement output.
- Prepare the participant discussion and revise the recurring arrangement from their actual contributions.
What to have ready
- Meeting records or a workable account, and the actual contributions of affected participants.
Where you come in
- Choose and review replacement work.
- Work through the recurring arrangement with participants and settle remaining decisions, inputs and exceptions.
- Authorize any later calendar changes or messages separately.
What you'll get
Checked AI replacement work and a participant-worked-through recurring meeting arrangement, including the remaining human coordination and unresolved objections.
You're done when
Participants have worked through which recurring meeting work AI will take over and how remaining decisions or coordination will happen, using checked AI replacement work and a shared account of the new arrangement.
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. ### 1. Find a recurring meeting and understand its work Help me replace or substantially shorten a recurring meeting by doing the work you can take over. First inspect whether you can access my calendar, emails, company chat, agendas, and meeting transcripts. Use the sources available and say what you could inspect. If you have access, identify recurring meetings and examine their purpose, attendees, and what actually happens in them. Read across several occurrences where possible. Find a promising candidate and explain why. Ask only for context you cannot establish from the available material. If access is missing, investigate whether an available connection would help and explain why these sources are useful. Offer to interview me about a recurring meeting I think could be replaced. Ask one vivid, focused question at a time about who attends, why they meet, and what happens from beginning to end. Use what I have already told you; if some sources are available, build on those. ### 2. Propose replacement work and the time it could save Identify specific work you can take over. - For information sharing, offer to gather updates and produce the briefing. - For clear decisions, offer to assemble the evidence, apply agreed criteria, and prepare recommendations for the people who decide. - For project work or prototypes, establish what the work is meant to accomplish, who it serves, and what a useful result would look like. Look through available material for existing work, examples, comparable products, or approaches you can build on. Ask me about anything essential you cannot establish. Use what you learn to propose a concrete output and the steps you will take to produce it. Keep this as a proposal until I select the work below. Show what you could complete before the next meeting, what still benefits from people meeting, and how much shorter the meeting could be. Ground any time estimate in the agenda, transcripts, or my account. Partial replacement is useful: if you can do two-thirds of the work, propose a much shorter meeting for the remainder. ### 3. Agree on the work and produce it Ask which work I want you to take over and wait for my selection before producing the replacement work. If I have already explicitly selected the work described above, use that selection. Carry out the selected work using the available sources and tools. If subagents are available and independent parts of the agreed work would benefit from parallel effort, delegate those parts. For example, one agent could gather project updates while another investigates exceptions. Give each agent a clear task, relevant context, and an expected output. Manage the agents yourself, check their evidence, reconcile conflicting findings, and combine their work into one coherent result. If delegation would not help or agents are unavailable, do the work yourself. ### 4. Check the result and review what remains Produce the actual briefing, decision material, prototype, or other agreed output. Ask me only for essential missing inputs. Check the result against the agreed purpose and sources, test any prototype’s main interactions, and fix problems before delivery. Show me the result for review and incorporate my corrections. Finish with a short remaining agenda based on what you actually completed, or explain why the completed work could replace this occurrence entirely. Identify any unfinished work and how it affects the proposed time saving. ### 5. Work through the recurring arrangement with participants Prepare a short working brief showing the checked AI output, what recurring work it can take over, the remaining decisions or coordination and the proposed use of everyone's meeting time. Bring the actual participants into working through that arrangement. I can host the discussion and provide notes, a transcript or their contributions in an agreed working document. Do not substitute a simulated audience or my assumptions for participants' actual involvement. Work through who supplies inputs, how the AI output reaches people, how they correct exceptions and where remaining human decisions happen. Record what changes in the recurring arrangement, actual participant responses and unresolved objections. Revise the role brief and remaining agenda from their contributions. A checked briefing or a case for cancelling one occurrence is preparation; it does not alone complete this recurring shared-work change. The move can finish with participants working through the new recurring practice together. Calendar cancellation, sending announcements and live adoption remain separately authorized actions; do not require them merely to complete joint preparation. If actual participation is absent, identify the unfinished work plainly. Leave the decision to apply calendar changes to me; obtain authorization before calendar changes or messages to attendees. 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
Cancel a meeting. Have AI do its job.
What the AI will do
- Investigate the recurring meeting, propose work to take over, and produce and check the selected replacement output.
- Prepare the participant discussion and revise the recurring arrangement from their actual contributions.
What you can provide
- Meeting records or a workable account, and the actual contributions of affected participants.
Where you'll take part
- Choose and review replacement work.
- Work through the recurring arrangement with participants and settle remaining decisions, inputs and exceptions.
- Authorize any later calendar changes or messages separately.
What you'll get
Checked AI replacement work and a participant-worked-through recurring meeting arrangement, including the remaining human coordination and unresolved objections.
Activity context
Find a recurring meeting whose work AI can take on. Replacing two-thirds of a meeting and giving everyone that time back counts, too. Work through the recurring replacement arrangement with the people who attend.
For the user
Have AI investigate a recurring meeting, do selected replacement work and check it. Then work through the recurring arrangement with actual participants and provide their contributions. The move may end with joint preparation; changing the calendar is separate.
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
1. Find a recurring meeting and understand its work
Help me replace or substantially shorten a recurring meeting by doing the work you can take over. First inspect whether you can access my calendar, emails, company chat, agendas, and meeting transcripts. Use the sources available and say what you could inspect.
If you have access, identify recurring meetings and examine their purpose, attendees, and what actually happens in them. Read across several occurrences where possible. Find a promising candidate and explain why. Ask only for context you cannot establish from the available material.
If access is missing, investigate whether an available connection would help and explain why these sources are useful. Offer to interview me about a recurring meeting I think could be replaced. Ask one vivid, focused question at a time about who attends, why they meet, and what happens from beginning to end. Use what I have already told you; if some sources are available, build on those.
2. Propose replacement work and the time it could save
Identify specific work you can take over.
-
For information sharing, offer to gather updates and produce the briefing.
-
For clear decisions, offer to assemble the evidence, apply agreed criteria, and prepare recommendations for the people who decide.
-
For project work or prototypes, establish what the work is meant to accomplish, who it serves, and what a useful result would look like.
Look through available material for existing work, examples, comparable products, or approaches you can build on. Ask me about anything essential you cannot establish.
Use what you learn to propose a concrete output and the steps you will take to produce it. Keep this as a proposal until I select the work below.
Show what you could complete before the next meeting, what still benefits from people meeting, and how much shorter the meeting could be. Ground any time estimate in the agenda, transcripts, or my account. Partial replacement is useful: if you can do two-thirds of the work, propose a much shorter meeting for the remainder.
3. Agree on the work and produce it
Ask which work I want you to take over and wait for my selection before producing the replacement work. If I have already explicitly selected the work described above, use that selection. Carry out the selected work using the available sources and tools.
If subagents are available and independent parts of the agreed work would benefit from parallel effort, delegate those parts. For example, one agent could gather project updates while another investigates exceptions. Give each agent a clear task, relevant context, and an expected output. Manage the agents yourself, check their evidence, reconcile conflicting findings, and combine their work into one coherent result. If delegation would not help or agents are unavailable, do the work yourself.
4. Check the result and review what remains
Produce the actual briefing, decision material, prototype, or other agreed output. Ask me only for essential missing inputs. Check the result against the agreed purpose and sources, test any prototype’s main interactions, and fix problems before delivery.
Show me the result for review and incorporate my corrections.
Finish with a short remaining agenda based on what you actually completed, or explain why the completed work could replace this occurrence entirely. Identify any unfinished work and how it affects the proposed time saving.
5. Work through the recurring arrangement with participants
Prepare a short working brief showing the checked AI output, what recurring work it can take over, the remaining decisions or coordination and the proposed use of everyone's meeting time. Bring the actual participants into working through that arrangement. I can host the discussion and provide notes, a transcript or their contributions in an agreed working document. Do not substitute a simulated audience or my assumptions for participants' actual involvement.
Work through who supplies inputs, how the AI output reaches people, how they correct exceptions and where remaining human decisions happen. Record what changes in the recurring arrangement, actual participant responses and unresolved objections. Revise the role brief and remaining agenda from their contributions. A checked briefing or a case for cancelling one occurrence is preparation; it does not alone complete this recurring shared-work change.
The move can finish with participants working through the new recurring practice together. Calendar cancellation, sending announcements and live adoption remain separately authorized actions; do not require them merely to complete joint preparation. If actual participation is absent, identify the unfinished work plainly.
Leave the decision to apply calendar changes to me; obtain authorization before calendar changes or messages to attendees.
Done when
Participants have worked through which recurring meeting work AI will take over and how remaining decisions or coordination will happen, using checked AI replacement work and a shared account of the new arrangement.
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.