Find key moments in a long recording.
Find the moment a decision changed, the strongest quote, or the explanation you need inside a long recording.
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
- Examine the recording and return a useful selection of moments with source references, timestamps where available, and explanations.
What to have ready
- A recording, accessible link, or transcript; a topic, question, or intended use if you have one.
Where you come in
- Clarify what makes a moment useful and choose the breadth of the selection.
What you'll get
You have a navigable selection of important moments, grounded in the available recording or transcript, with context and accurate time references where supported.
You're done when
You have a navigable selection of important moments, grounded in the available recording or transcript, with context and accurate time references where supported.
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. Find the key moments in this long recording for the purpose I have in mind. ### 1. Establish what matters and inspect access. Read my request and inspect the recording, metadata, and any available transcript. Determine whether you can access audio, video, timecoded text, or only an untimed transcript. Try supported tools and help me provide another usable form if access is missing. Do not claim an exact moment or quotation from content you could not inspect. Use relevant available emails, messages and chats, agendas, meeting transcripts, documents, and project files to understand the subject, participants, and my intended use. Relevant context may reveal that I need decisions, objections, examples, or strong quotations rather than a generic summary. Ask a focused question if the selection criteria remain unclear. Offer two useful treatments when appropriate, such as five essential moments with context or a fuller thematic index. Explain the difference and wait when the choice would change the search. Otherwise proceed with criteria grounded in my request. ### 2. Examine the full accessible recording. Scan or process the full available span, then inspect candidate moments in their surrounding context. Follow the development of important topics across the recording rather than stopping at early keyword matches. Identify later corrections, changed decisions, qualifications, or withdrawals that affect an earlier passage. Use actual recording timecodes. Distinguish elapsed playback time from meeting clock time; account for separate files or segments so every reference identifies the right source. If a transcript lacks timing, provide section or passage references and say that timestamps are unavailable. Mark approximate boundaries when the tool cannot support exact ones. ### 3. Select and explain the moments. Choose moments against the agreed criteria, balancing significance and useful coverage. For each, provide a clear label, start and end time where supported, speaker if established, a concise account or accurate short quotation, and why it matters. Include enough preceding or following context to prevent a misleading extract. Link related moments when a later passage changes an earlier one. Distinguish an announced decision from a suggestion, and a memorable assertion from evidence that it is true. When identities or meanings are ambiguous, state the issue and ask if my context could resolve it. Do not infer a speaker’s identity solely from a guess about their voice. ### 4. Verify and deliver a usable index. - Revisit the selected spans to check timestamps, quotations, speaker labels, and context. - Confirm that time links work where the source supports them. - Remove repetitions unless their contrast is useful. - Explain the actual coverage if any part of the recording was unavailable or unprocessed. Deliver the selected moments in a concise, navigable list or table, with source links or identifying details. Incorporate my corrections or adjust the selection if my priorities change. Finish with the index itself; extracting or publishing clips is a separate task unless I request it. 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
Find key moments in a long recording.
What the AI will do
- Examine the recording and return a useful selection of moments with source references, timestamps where available, and explanations.
What you can provide
- A recording, accessible link, or transcript; a topic, question, or intended use if you have one.
Where you'll take part
- Clarify what makes a moment useful and choose the breadth of the selection.
What you'll get
You have a navigable selection of important moments, grounded in the available recording or transcript, with context and accurate time references where supported.
Activity context
Find the moment a decision changed, the strongest quote, or the explanation you need inside a long recording.
For the user
Share the recording or a transcript and what you hope to find, if you know. The AI can use related agendas, correspondence, and project material to identify what matters. You’ll clarify the selection criteria or choose between a short highlights list and a fuller index.
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
Find the key moments in this long recording for the purpose I have in mind.
1. Establish what matters and inspect access.
Read my request and inspect the recording, metadata, and any available transcript. Determine whether you can access audio, video, timecoded text, or only an untimed transcript. Try supported tools and help me provide another usable form if access is missing. Do not claim an exact moment or quotation from content you could not inspect.
Use relevant available emails, messages and chats, agendas, meeting transcripts, documents, and project files to understand the subject, participants, and my intended use. Relevant context may reveal that I need decisions, objections, examples, or strong quotations rather than a generic summary.
Ask a focused question if the selection criteria remain unclear. Offer two useful treatments when appropriate, such as five essential moments with context or a fuller thematic index. Explain the difference and wait when the choice would change the search. Otherwise proceed with criteria grounded in my request.
2. Examine the full accessible recording.
Scan or process the full available span, then inspect candidate moments in their surrounding context. Follow the development of important topics across the recording rather than stopping at early keyword matches. Identify later corrections, changed decisions, qualifications, or withdrawals that affect an earlier passage.
Use actual recording timecodes. Distinguish elapsed playback time from meeting clock time; account for separate files or segments so every reference identifies the right source. If a transcript lacks timing, provide section or passage references and say that timestamps are unavailable. Mark approximate boundaries when the tool cannot support exact ones.
3. Select and explain the moments.
Choose moments against the agreed criteria, balancing significance and useful coverage. For each, provide a clear label, start and end time where supported, speaker if established, a concise account or accurate short quotation, and why it matters. Include enough preceding or following context to prevent a misleading extract.
Link related moments when a later passage changes an earlier one. Distinguish an announced decision from a suggestion, and a memorable assertion from evidence that it is true. When identities or meanings are ambiguous, state the issue and ask if my context could resolve it. Do not infer a speaker’s identity solely from a guess about their voice.
4. Verify and deliver a usable index.
- Revisit the selected spans to check timestamps, quotations, speaker labels, and context.
- Confirm that time links work where the source supports them.
- Remove repetitions unless their contrast is useful.
- Explain the actual coverage if any part of the recording was unavailable or unprocessed.
Deliver the selected moments in a concise, navigable list or table, with source links or identifying details. Incorporate my corrections or adjust the selection if my priorities change. Finish with the index itself; extracting or publishing clips is a separate task unless I request it.
Done when
You have a navigable selection of important moments, grounded in the available recording or transcript, with context and accurate time references where supported.
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.