Turn scribbled notes into an action plan.
The useful plan may already be in your notes. Let AI work out what the fragments refer to, what still matters, and what has to happen first.
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 your notes and investigate related conversations and project records to recover their meaning and current commitments.
- Turn the work into a sequenced action plan, checking dependencies and separating agreed commitments from proposed ones.
What to have ready
- A photo of scribbles, rough notes, copied text, or a link to the notes; a project name helps the AI find the surrounding record.
Where you come in
- Clarify a few consequential ambiguities and confirm proposed owners, dates, or priorities that the record does not settle.
What you'll get
You have a usable action plan with a clear starting point, dependencies, confirmed commitments, and visibly unresolved details.
You're done when
You have a usable action plan with a clear starting point, dependencies, confirmed commitments, and visibly unresolved details.
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 turn scribbled notes into an action plan. Recover what they mean, establish what remains to be done, and produce a plan someone can actually start using. ### 1. Read the notes and establish their purpose Accept a photograph, scan, typed fragments, voice transcription, or a link. Inspect the original where possible, including arrows, groupings, crossed-out text, margins, and headings. Preserve a faithful working transcription separate from your interpretation. Mark unreadable words; do not silently replace them with a plausible task. Use what I supplied to identify the project, meeting, people, and intended outcome. Ask what the notes are for if that is unclear: for example, my personal follow-through after a meeting or a plan for a whole team. Wait before organizing around an unresolved purpose. Welcome an informal answer; do not ask me to prepare a cleaner version. ### 2. Recover the surrounding record Try relevant available access. Search emails, chats and other messages, calendar events and attendee lists, meeting transcripts, project documents, task records, and relevant company data using names, phrases, dates, and project references from the notes. Look for: - The objective and what successful completion means. - What an abbreviation or fragment refers to, and which people were involved. - Decisions, accepted responsibilities, deadlines, dependencies, and constraints. - Work completed since the notes were written, and later decisions that amend or replace earlier ones. Use participant roles and their actual correspondence to understand who needs the plan and what detail they need. Do not infer that a person accepted a task because they attended the meeting or were mentioned next to it. Cite the records supporting consequential commitments, with dates or locations that make them recoverable. If access fails, investigate connection or export alternatives and ask for only the missing material that matters. Offer help with the specific export or upload. With just the notes, produce a useful provisional plan and identify what cannot be corroborated; missing records must not become invented history. For a large project history, divide investigation into bounded workstreams or date ranges. Give agents explicit sources, questions, and a requested return: findings, supporting references, contradictions, and coverage gaps. Use fresh contexts and successive waves where available. Without agents, use manageable passes or fresh-session handoffs containing the notes, source index, settled decisions, and remaining searches. Keep a coverage record and reconcile overlaps before planning. ### 3. Turn fragments into actual work Classify each meaningful item as an action, decision, question, reference, idea, or completed/cancelled work. Combine genuine duplicates while preserving differences in deliverable or audience. Translate actions into a verb, an object, and an observable result: “budget” might mean “prepare the revised cost estimate for the sponsor,” but only if the evidence supports that reading. Separate source-established tasks from useful actions you propose to bridge a gap. Link every substantial action to the note or contextual evidence that prompted it. Keep interesting ideas that do not serve the current objective outside the active plan. Resolve ambiguities that change the work. Ask focused questions one at a time and wait before dependent choices. When two interpretations are credible, show their practical difference, recommend one if justified, and ask me to choose. Continue clarifying independent items meanwhile. Do not require confirmation of every straightforward transcription or sourced fact. ### 4. Build and check the sequence Work backward from the desired result to identify prerequisites, decisions, inputs, and handoffs. Then arrange a feasible forward sequence. Distinguish a hard deadline from a proposed target and an accepted owner from a suggested one. Check that parallel tasks do not assume the same unavailable person or resource. Where evidence is missing, ask me to confirm proposed owners or dates before presenting them as commitments. For each active task, include its result, owner or unresolved owner, timing or trigger, and dependency. Add enough detail to start without another round of interpretation. Identify the first available action. Keep a short unresolved-decisions section separate from executable work. Check the finished plan against the original notes and the later record: nothing important disappeared, cancelled work did not return, and no task depends on its own downstream result. If an independent review would help, give a fresh reviewer the plan and source references, ask for omissions and infeasible dependencies, and repair supported findings. Describe any same-context check accurately. ### 5. Deliver the plan Present the usable plan in the simplest appropriate format, with the starting action first and a short explanation of consequential assumptions. Incorporate my corrections and recheck affected dependencies. Finish with confirmed work, proposed work awaiting decisions, and any source limitation clearly distinguished. Creating the plan does not include assigning tasks in external systems or contacting people. 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 scribbled notes into an action plan.
What the AI will do
- Read your notes and investigate related conversations and project records to recover their meaning and current commitments.
- Turn the work into a sequenced action plan, checking dependencies and separating agreed commitments from proposed ones.
What you can provide
- A photo of scribbles, rough notes, copied text, or a link to the notes; a project name helps the AI find the surrounding record.
Where you'll take part
- Clarify a few consequential ambiguities and confirm proposed owners, dates, or priorities that the record does not settle.
What you'll get
You have a usable action plan with a clear starting point, dependencies, confirmed commitments, and visibly unresolved details.
Activity context
The useful plan may already be in your notes. Let AI work out what the fragments refer to, what still matters, and what has to happen first.
For the user
Share the notes in whatever shape they are in. The AI will use relevant records to fill in context and ask you about details that affect the plan. You review decisions it cannot establish, rather than having to organize the notes yourself.
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 turn scribbled notes into an action plan. Recover what they mean, establish what remains to be done, and produce a plan someone can actually start using.
1. Read the notes and establish their purpose
Accept a photograph, scan, typed fragments, voice transcription, or a link. Inspect the original where possible, including arrows, groupings, crossed-out text, margins, and headings. Preserve a faithful working transcription separate from your interpretation. Mark unreadable words; do not silently replace them with a plausible task.
Use what I supplied to identify the project, meeting, people, and intended outcome. Ask what the notes are for if that is unclear: for example, my personal follow-through after a meeting or a plan for a whole team. Wait before organizing around an unresolved purpose. Welcome an informal answer; do not ask me to prepare a cleaner version.
2. Recover the surrounding record
Try relevant available access. Search emails, chats and other messages, calendar events and attendee lists, meeting transcripts, project documents, task records, and relevant company data using names, phrases, dates, and project references from the notes. Look for:
- The objective and what successful completion means.
- What an abbreviation or fragment refers to, and which people were involved.
- Decisions, accepted responsibilities, deadlines, dependencies, and constraints.
- Work completed since the notes were written, and later decisions that amend or replace earlier ones.
Use participant roles and their actual correspondence to understand who needs the plan and what detail they need. Do not infer that a person accepted a task because they attended the meeting or were mentioned next to it. Cite the records supporting consequential commitments, with dates or locations that make them recoverable.
If access fails, investigate connection or export alternatives and ask for only the missing material that matters. Offer help with the specific export or upload. With just the notes, produce a useful provisional plan and identify what cannot be corroborated; missing records must not become invented history.
For a large project history, divide investigation into bounded workstreams or date ranges. Give agents explicit sources, questions, and a requested return: findings, supporting references, contradictions, and coverage gaps. Use fresh contexts and successive waves where available. Without agents, use manageable passes or fresh-session handoffs containing the notes, source index, settled decisions, and remaining searches. Keep a coverage record and reconcile overlaps before planning.
3. Turn fragments into actual work
Classify each meaningful item as an action, decision, question, reference, idea, or completed/cancelled work. Combine genuine duplicates while preserving differences in deliverable or audience. Translate actions into a verb, an object, and an observable result: “budget” might mean “prepare the revised cost estimate for the sponsor,” but only if the evidence supports that reading.
Separate source-established tasks from useful actions you propose to bridge a gap. Link every substantial action to the note or contextual evidence that prompted it. Keep interesting ideas that do not serve the current objective outside the active plan.
Resolve ambiguities that change the work. Ask focused questions one at a time and wait before dependent choices. When two interpretations are credible, show their practical difference, recommend one if justified, and ask me to choose. Continue clarifying independent items meanwhile. Do not require confirmation of every straightforward transcription or sourced fact.
4. Build and check the sequence
Work backward from the desired result to identify prerequisites, decisions, inputs, and handoffs. Then arrange a feasible forward sequence. Distinguish a hard deadline from a proposed target and an accepted owner from a suggested one. Check that parallel tasks do not assume the same unavailable person or resource. Where evidence is missing, ask me to confirm proposed owners or dates before presenting them as commitments.
For each active task, include its result, owner or unresolved owner, timing or trigger, and dependency. Add enough detail to start without another round of interpretation. Identify the first available action. Keep a short unresolved-decisions section separate from executable work.
Check the finished plan against the original notes and the later record: nothing important disappeared, cancelled work did not return, and no task depends on its own downstream result. If an independent review would help, give a fresh reviewer the plan and source references, ask for omissions and infeasible dependencies, and repair supported findings. Describe any same-context check accurately.
5. Deliver the plan
Present the usable plan in the simplest appropriate format, with the starting action first and a short explanation of consequential assumptions. Incorporate my corrections and recheck affected dependencies. Finish with confirmed work, proposed work awaiting decisions, and any source limitation clearly distinguished. Creating the plan does not include assigning tasks in external systems or contacting people.
Done when
You have a usable action plan with a clear starting point, dependencies, confirmed commitments, and visibly unresolved details.
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.