Read a sensitive message through its recipient’s eyes.
A message can be accurate and still land badly. Look closely at what this recipient has said and experienced, then examine the lines they may read differently from you.
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
- Finds relevant correspondence and project history to understand the recipient and the issue.
- Reviews specific lines through evidence-informed recipient perspectives and writes a revised message.
What to have ready
- The message or a rough draft, plus the recipient’s identity if it is not apparent.
- Any private intention or constraint that the available record would not reveal.
Where you come in
- Clarify your intended outcome or an important ambiguity.
- Review changes that alter a request, concession, or commitment.
What you'll get
A line-specific reading of the message and a complete revision that preserves your intent, with known concerns distinguished from plausible reactions.
You're done when
You have the complete revised message, understand its most consequential possible readings, and can see which conclusions come from actual history and which remain simulations.
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. ### Start with the actual message Help me read a sensitive message through its recipient's eyes and improve it. Read the entire message before commenting. Establish whom it is for and the outcome I want, using what I have already supplied. If either is unclear, investigate the available context first and ask only for what remains necessary. Preserve my substantive position; sensitivity is not a reason to remove the issue I need to raise. ### Find the relationship and issue history Inspect and try available access to relevant emails, chats and other messages, calendar interactions, linked transcripts, shared documents, project records, and company data. Search the recipient's name, the issue, cited events, and distinctive phrases. Look for the actual request or disagreement, prior commitments, recent changes, the recipient's expressed priorities, and earlier exchanges showing how they communicate. Follow related threads rather than reading one isolated sentence as a complete account. Use calendar and project information to understand role, timing, responsibilities, and shared events. Use company or project data to check claims about performance, workload, resources, or deadlines when the message depends on them. Keep dates and source references for findings that materially affect the reading. Distinguish the recipient's own words from another person's characterization of them. If a useful connection is unavailable, investigate an export or another permitted route before asking me to collect material. Explain the specific missing evidence and help me provide it. With only the message, continue as a text-based review and identify the recipient assumptions that cannot be checked. Do not invent a relationship history or a psychological profile. ### Establish the intended meaning Give me a short account of what the message appears to ask, assert, and imply. Separate explicit content from your inference. Identify any consequential ambiguity—such as whether I am declining, negotiating, escalating, or asking for an explanation—and ask one focused question when the record does not settle it. Wait before revising that part. Confirm any answer or decision you propose on my behalf. ### Examine plausible readings independently Use separate agents for distinct recipients or materially different, evidence-supported readings when that would improve the analysis. Avoid manufacturing multiple personalities just to fill a team. Give each agent the exact message, a bounded recipient brief, relevant source references, known concerns, and uncertainties. Do not supply the author's explanation of how the wording was intended to land; provide only legitimate situational facts needed to read it. Have each independently examine specific lines for: - The request, accusation, promise, or status signal it might hear. - Wording that interacts with a documented concern or earlier exchange. - A plausible charitable reading and a plausible troublesome reading where both fit. - Missing context that could change its judgment. Keep initial findings separate until all relevant passes finish. Split a large relationship history into bounded searches and pass forward sourced findings, not an unexamined archive. Use successive waves if needed. Without agents, use manageable passes or a fresh-session reviewer with an explicit source handoff, and describe whether review shared drafting context. Simulations are hypotheses, never testimony from the recipient. ### Revise without losing the point Show the most consequential line-level findings with the original wording, possible reading, supporting context, and a proposed change. Focus on changes that matter. If alternatives would represent different substantive choices—such as a direct request for correction versus an invitation to discuss—explain their practical difference and ask me to settle the choice before finalizing dependent wording. Write the complete revised message. Make the request and desired outcome easy to identify, retain necessary facts, and remove avoidable implication or ambiguity. Match a voice supported by my supplied writing. Do not add a concession, apology, threat, deadline, or promise unless it is already established or I confirm it. ### Check the final message Have the reviewer inspect the revision for the original trouble spots and any new ambiguity. Check factual statements and commitments against sources. Deliver the revised message in full, with concise separate notes on the changes that most affect interpretation and the remaining uncertainty. If missing context limits the review, state that limit alongside the result. Do not send the message or contact anyone. 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
Read a sensitive message through its recipient’s eyes.
What the AI will do
- Finds relevant correspondence and project history to understand the recipient and the issue.
- Reviews specific lines through evidence-informed recipient perspectives and writes a revised message.
What you can provide
- The message or a rough draft, plus the recipient’s identity if it is not apparent.
- Any private intention or constraint that the available record would not reveal.
Where you'll take part
- Clarify your intended outcome or an important ambiguity.
- Review changes that alter a request, concession, or commitment.
What you'll get
A line-specific reading of the message and a complete revision that preserves your intent, with known concerns distinguished from plausible reactions.
Activity context
A message can be accurate and still land badly. Look closely at what this recipient has said and experienced, then examine the lines they may read differently from you.
For the user
Provide the message and identify its recipient. The AI will first look for relevant history, then explain how particular lines could be understood and revise the message. You will clarify consequential ambiguity and review any proposed change to your position.
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
Start with the actual message
Help me read a sensitive message through its recipient's eyes and improve it. Read the entire message before commenting. Establish whom it is for and the outcome I want, using what I have already supplied. If either is unclear, investigate the available context first and ask only for what remains necessary. Preserve my substantive position; sensitivity is not a reason to remove the issue I need to raise.
Find the relationship and issue history
Inspect and try available access to relevant emails, chats and other messages, calendar interactions, linked transcripts, shared documents, project records, and company data. Search the recipient's name, the issue, cited events, and distinctive phrases. Look for the actual request or disagreement, prior commitments, recent changes, the recipient's expressed priorities, and earlier exchanges showing how they communicate. Follow related threads rather than reading one isolated sentence as a complete account.
Use calendar and project information to understand role, timing, responsibilities, and shared events. Use company or project data to check claims about performance, workload, resources, or deadlines when the message depends on them. Keep dates and source references for findings that materially affect the reading. Distinguish the recipient's own words from another person's characterization of them.
If a useful connection is unavailable, investigate an export or another permitted route before asking me to collect material. Explain the specific missing evidence and help me provide it. With only the message, continue as a text-based review and identify the recipient assumptions that cannot be checked. Do not invent a relationship history or a psychological profile.
Establish the intended meaning
Give me a short account of what the message appears to ask, assert, and imply. Separate explicit content from your inference. Identify any consequential ambiguity—such as whether I am declining, negotiating, escalating, or asking for an explanation—and ask one focused question when the record does not settle it. Wait before revising that part. Confirm any answer or decision you propose on my behalf.
Examine plausible readings independently
Use separate agents for distinct recipients or materially different, evidence-supported readings when that would improve the analysis. Avoid manufacturing multiple personalities just to fill a team. Give each agent the exact message, a bounded recipient brief, relevant source references, known concerns, and uncertainties. Do not supply the author's explanation of how the wording was intended to land; provide only legitimate situational facts needed to read it.
Have each independently examine specific lines for:
- The request, accusation, promise, or status signal it might hear.
- Wording that interacts with a documented concern or earlier exchange.
- A plausible charitable reading and a plausible troublesome reading where both fit.
- Missing context that could change its judgment.
Keep initial findings separate until all relevant passes finish. Split a large relationship history into bounded searches and pass forward sourced findings, not an unexamined archive. Use successive waves if needed. Without agents, use manageable passes or a fresh-session reviewer with an explicit source handoff, and describe whether review shared drafting context. Simulations are hypotheses, never testimony from the recipient.
Revise without losing the point
Show the most consequential line-level findings with the original wording, possible reading, supporting context, and a proposed change. Focus on changes that matter. If alternatives would represent different substantive choices—such as a direct request for correction versus an invitation to discuss—explain their practical difference and ask me to settle the choice before finalizing dependent wording.
Write the complete revised message. Make the request and desired outcome easy to identify, retain necessary facts, and remove avoidable implication or ambiguity. Match a voice supported by my supplied writing. Do not add a concession, apology, threat, deadline, or promise unless it is already established or I confirm it.
Check the final message
Have the reviewer inspect the revision for the original trouble spots and any new ambiguity. Check factual statements and commitments against sources. Deliver the revised message in full, with concise separate notes on the changes that most affect interpretation and the remaining uncertainty. If missing context limits the review, state that limit alongside the result. Do not send the message or contact anyone.
Done when
You have the complete revised message, understand its most consequential possible readings, and can see which conclusions come from actual history and which remain simulations.
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.