Turn 10 docs into one clear one.
Turn a pile of overlapping documents into the one document someone actually needs to read.
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
- Read the documents and relevant context, reconcile overlap and versions, and write one coherent document.
- Trace important claims and decisions back to their sources.
What to have ready
- The documents, links, or folder; a purpose or audience if already known. Ten is a useful starting point, not a required count.
Where you come in
- Choose between useful structures and resolve consequential disagreements or missing decisions.
What you'll get
You have one coherent, editable document suited to its audience, with important source references and unresolved conflicts made explicit.
You're done when
You have one coherent, editable document suited to its audience, with important source references and unresolved conflicts made explicit.
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. Turn these overlapping documents into one clear, coherent document that serves the intended reader and purpose. ### 1. Understand the collection and intended result. Read all supplied documents, not just their summaries or filenames. Inventory their subjects, authors, dates, versions, and apparent purposes. Identify what is accessible and help me share inaccessible material through a supported route. Work with the collection available; do not insist on exactly ten documents. Use available connected email, messages and chats, meeting transcripts, documents, and project files to understand why these materials exist, who needs the combined result, and what subsequent decisions may have changed. Follow relevant references rather than collecting unrelated organizational material. Establish the intended audience, use, scope, and level of detail from this evidence and my request. Ask focused questions where the answers would improve the result. If two structures would serve different needs, show concrete alternatives—for example, a decision memo organized around the choice to make or a reference document organized by topic—with a brief sample outline and recommendation. Wait before committing to a structure when my choice would change the substance. Otherwise proceed with an explained, well-supported approach. ### 2. Reconcile the substance before writing. Build a working map of key claims, evidence, examples, decisions, and open questions across the documents. Identify duplicates, complementary detail, contradictory statements, and missing links in the argument. Preserve source locations so the final text can be checked. For conflicting versions, inspect dates, authorship, explicit approval or decision records, and later correspondence. A later file modification date alone does not establish that its content supersedes an earlier decision. Distinguish a replaced decision from a competing proposal or unresolved disagreement. Track partial amendments without discarding unaffected material. Ask me to resolve a conflict if it materially affects the combined document and the evidence cannot settle it. Present the competing readings and their implications clearly; two proposed formulations may make the choice easier. Wait for that decision before finalizing the affected passage, while continuing independent sections. Keep unresolved issues explicit if I cannot resolve them. ### 3. Write the document as a whole. Use the chosen structure to produce an actual document with a clear opening, logical sequence, and appropriate level of detail. Combine complementary information, eliminate repetition, explain necessary terms, and retain distinctive examples or qualifications that carry meaning. Do not assemble a stack of shortened summaries. Keep facts, decisions, recommendations, and open questions distinguishable. Preserve relevant source references in a form suited to the audience: links, footnotes, or a source appendix. Do not invent missing evidence or convert a disputed view into consensus for smoother prose. If the short main document needs supporting detail, place that detail in an organized appendix rather than dropping it silently. ### 4. Check coverage and deliver. - Compare the draft with the source map. - Confirm that every material point needed for the agreed purpose is represented or deliberately omitted for an explained reason. - Check factual claims, numbers, dates, quotations, and the current status of decisions. - Read the document on its own to identify unexplained references, broken logic, and repetition; revise them. Create and inspect an editable file where tools permit, or provide a complete supported text format. Present the usable document, explain any decisions still needed, and invite corrections to its purpose or argument. Incorporate my feedback and recheck the affected content. Finish with the combined document and its source trail, not an outline or a list of work for me to do. 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
Turn 10 docs into one clear one.
What the AI will do
- Read the documents and relevant context, reconcile overlap and versions, and write one coherent document.
- Trace important claims and decisions back to their sources.
What you can provide
- The documents, links, or folder; a purpose or audience if already known. Ten is a useful starting point, not a required count.
Where you'll take part
- Choose between useful structures and resolve consequential disagreements or missing decisions.
What you'll get
You have one coherent, editable document suited to its audience, with important source references and unresolved conflicts made explicit.
Activity context
Turn a pile of overlapping documents into the one document someone actually needs to read.
For the user
Share the documents in whatever form you have them. The AI can find related discussion and later decisions through available connections. You’ll help settle the intended audience, choose an organizing approach if needed, and resolve substantive conflicts the sources cannot settle.
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
Turn these overlapping documents into one clear, coherent document that serves the intended reader and purpose.
1. Understand the collection and intended result.
Read all supplied documents, not just their summaries or filenames. Inventory their subjects, authors, dates, versions, and apparent purposes. Identify what is accessible and help me share inaccessible material through a supported route. Work with the collection available; do not insist on exactly ten documents.
Use available connected email, messages and chats, meeting transcripts, documents, and project files to understand why these materials exist, who needs the combined result, and what subsequent decisions may have changed. Follow relevant references rather than collecting unrelated organizational material.
Establish the intended audience, use, scope, and level of detail from this evidence and my request. Ask focused questions where the answers would improve the result. If two structures would serve different needs, show concrete alternatives—for example, a decision memo organized around the choice to make or a reference document organized by topic—with a brief sample outline and recommendation. Wait before committing to a structure when my choice would change the substance. Otherwise proceed with an explained, well-supported approach.
2. Reconcile the substance before writing.
Build a working map of key claims, evidence, examples, decisions, and open questions across the documents. Identify duplicates, complementary detail, contradictory statements, and missing links in the argument. Preserve source locations so the final text can be checked.
For conflicting versions, inspect dates, authorship, explicit approval or decision records, and later correspondence. A later file modification date alone does not establish that its content supersedes an earlier decision. Distinguish a replaced decision from a competing proposal or unresolved disagreement. Track partial amendments without discarding unaffected material.
Ask me to resolve a conflict if it materially affects the combined document and the evidence cannot settle it. Present the competing readings and their implications clearly; two proposed formulations may make the choice easier. Wait for that decision before finalizing the affected passage, while continuing independent sections. Keep unresolved issues explicit if I cannot resolve them.
3. Write the document as a whole.
Use the chosen structure to produce an actual document with a clear opening, logical sequence, and appropriate level of detail. Combine complementary information, eliminate repetition, explain necessary terms, and retain distinctive examples or qualifications that carry meaning. Do not assemble a stack of shortened summaries.
Keep facts, decisions, recommendations, and open questions distinguishable. Preserve relevant source references in a form suited to the audience: links, footnotes, or a source appendix. Do not invent missing evidence or convert a disputed view into consensus for smoother prose. If the short main document needs supporting detail, place that detail in an organized appendix rather than dropping it silently.
4. Check coverage and deliver.
- Compare the draft with the source map.
- Confirm that every material point needed for the agreed purpose is represented or deliberately omitted for an explained reason.
- Check factual claims, numbers, dates, quotations, and the current status of decisions.
- Read the document on its own to identify unexplained references, broken logic, and repetition; revise them.
Create and inspect an editable file where tools permit, or provide a complete supported text format. Present the usable document, explain any decisions still needed, and invite corrections to its purpose or argument. Incorporate my feedback and recheck the affected content. Finish with the combined document and its source trail, not an outline or a list of work for me to do.
Done when
You have one coherent, editable document suited to its audience, with important source references and unresolved conflicts made explicit.
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.