Untangle email threads into a timeline of decisions.
Find out what was actually decided—and which decisions have since changed—without rereading every thread yourself.
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
- Reconstruct a dated, sourced decision history across the available channels.
- Show which decisions still stand and which were amended, reversed, or superseded.
What to have ready
- A thread, project, issue, or date range; connected records or shared exports can supply the history.
Where you come in
- Resolve important ambiguities about authority or meaning and choose the level of detail that is useful.
What you'll get
You have a traceable timeline of decisions and changes, a clear account of the current position, and an explicit list of unresolved conflicts or gaps.
You're done when
You have a traceable timeline of decisions and changes, a clear account of the current position, and an explicit list of unresolved conflicts or gaps.
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. Untangle the available correspondence into a timeline of decisions, carefully tracking when later decisions change earlier ones. ### 1. Establish the question and gather the record. Start with the thread, project, issue, or messages I supplied. Infer the relevant people and period from the material. Ask a focused question if the scope is too ambiguous to search usefully. Offer a concise current-position account or a fuller decision history if either could serve my purpose; retain source traceability in both. Inspect and try available email, WhatsApp and other messaging or chat access, meeting transcripts, shared documents, and project files. Follow references between records and search across the relevant period, including later material that might alter earlier decisions. Help me share exports or missing material if a channel is unavailable. Keep a source inventory with coverage dates and access gaps; do not imply that inaccessible channels were checked. ### 2. Reconstruct the chronology. Read complete exchanges where necessary to understand a decision. Record the timestamp, author or participants, channel, source reference, and relevant wording. Distinguish a message’s sent date, a meeting’s occurrence date, and a future effective date. Preserve time zones when they could affect ordering. Flag undated records or unresolved ordering rather than assigning invented dates. Separate proposals, questions, preferences, decisions, assignments, and acknowledgments. A forwarded message, quoted passage, or repeated summary is not a new decision. Consolidate duplicates while retaining their source references. Identify who appears authorized to decide when that matters, using evidence or asking me rather than assuming every participant can change the plan. ### 3. Track decisions through their changes. For each consequential decision, trace subsequent discussion and evidence of amendment, replacement, reversal, or withdrawal. Link the later event to the earlier decision and explain exactly what changed and what remained in force. Partial changes should not erase the rest of a decision. Do not assume the latest mention wins: it may be a suggestion, a misunderstanding, or a retrospective description. Where accounts conflict, show both with dates and sources, state the ambiguity, and ask a focused question if my knowledge could resolve it. Wait before treating a disputed interpretation as settled. Otherwise retain it as unresolved in the final record. ### 4. Deliver and verify the history. Lead with the current position: decisions that appear in force, associated owners or deadlines where established, and matters still open. Provide a timeline with date, event or decision, decision-maker where known, source, and relationship to previous decisions. Include effective dates separately where relevant. The result should let me follow a current decision back to its original adoption and later changes. - Check every current-state claim against the underlying sources and search for later contradictory evidence within the accessible scope. - Incorporate my corrections while distinguishing my account from documentary evidence. - Deliver an editable record with working links or enough identifying detail to retrieve each source. - State the actual coverage and material gaps; do not portray an incomplete record as a complete project history. 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
Untangle email threads into a timeline of decisions.
What the AI will do
- Reconstruct a dated, sourced decision history across the available channels.
- Show which decisions still stand and which were amended, reversed, or superseded.
What you can provide
- A thread, project, issue, or date range; connected records or shared exports can supply the history.
Where you'll take part
- Resolve important ambiguities about authority or meaning and choose the level of detail that is useful.
What you'll get
You have a traceable timeline of decisions and changes, a clear account of the current position, and an explicit list of unresolved conflicts or gaps.
Activity context
Find out what was actually decided—and which decisions have since changed—without rereading every thread yourself.
For the user
Share a thread, project name, or collection of messages. The AI can bring together relevant email, WhatsApp and other chats, meeting transcripts, and documents. You’ll help settle any disputed interpretation and choose whether you need a concise current-state account or a fuller decision history.
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
Untangle the available correspondence into a timeline of decisions, carefully tracking when later decisions change earlier ones.
1. Establish the question and gather the record.
Start with the thread, project, issue, or messages I supplied. Infer the relevant people and period from the material. Ask a focused question if the scope is too ambiguous to search usefully. Offer a concise current-position account or a fuller decision history if either could serve my purpose; retain source traceability in both.
Inspect and try available email, WhatsApp and other messaging or chat access, meeting transcripts, shared documents, and project files. Follow references between records and search across the relevant period, including later material that might alter earlier decisions. Help me share exports or missing material if a channel is unavailable. Keep a source inventory with coverage dates and access gaps; do not imply that inaccessible channels were checked.
2. Reconstruct the chronology.
Read complete exchanges where necessary to understand a decision. Record the timestamp, author or participants, channel, source reference, and relevant wording. Distinguish a message’s sent date, a meeting’s occurrence date, and a future effective date. Preserve time zones when they could affect ordering. Flag undated records or unresolved ordering rather than assigning invented dates.
Separate proposals, questions, preferences, decisions, assignments, and acknowledgments. A forwarded message, quoted passage, or repeated summary is not a new decision. Consolidate duplicates while retaining their source references. Identify who appears authorized to decide when that matters, using evidence or asking me rather than assuming every participant can change the plan.
3. Track decisions through their changes.
For each consequential decision, trace subsequent discussion and evidence of amendment, replacement, reversal, or withdrawal. Link the later event to the earlier decision and explain exactly what changed and what remained in force. Partial changes should not erase the rest of a decision.
Do not assume the latest mention wins: it may be a suggestion, a misunderstanding, or a retrospective description. Where accounts conflict, show both with dates and sources, state the ambiguity, and ask a focused question if my knowledge could resolve it. Wait before treating a disputed interpretation as settled. Otherwise retain it as unresolved in the final record.
4. Deliver and verify the history.
Lead with the current position: decisions that appear in force, associated owners or deadlines where established, and matters still open. Provide a timeline with date, event or decision, decision-maker where known, source, and relationship to previous decisions. Include effective dates separately where relevant. The result should let me follow a current decision back to its original adoption and later changes.
- Check every current-state claim against the underlying sources and search for later contradictory evidence within the accessible scope.
- Incorporate my corrections while distinguishing my account from documentary evidence.
- Deliver an editable record with working links or enough identifying detail to retrieve each source.
- State the actual coverage and material gaps; do not portray an incomplete record as a complete project history.
Done when
You have a traceable timeline of decisions and changes, a clear account of the current position, and an explicit list of unresolved conflicts or gaps.
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.