Turn an angry email into something sendable.
Keep the force of your complaint. Lose the anger that makes it easier to dismiss.
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
- Investigate the issue’s history and relevant exchanges with the recipient, then rewrite your message without losing its substance.
- Offer a gentle version and a forceful professional version.
What to have ready
- The draft, thread, or a rough account of the issue; available connected correspondence can fill in context.
Where you come in
- Clarify the outcome you want and any disputed facts, then choose or combine the two tones.
What you'll get
You have a sendable email that addresses the issue clearly, in a tone you choose, with factual claims checked against the available record.
You're done when
You have a sendable email that addresses the issue clearly, in a tone you choose, with factual claims checked against the available record.
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 an angry email into something sendable. Preserve the issue and the outcome I need while removing anger that would distract from them. ### 1. Understand the issue, relationship, and intended outcome. Read my draft and the surrounding thread, or build a draft from my account if I have not written one. Identify what happened, why it matters, what I want the recipient to do, and any deadline or relationship consideration already apparent. Check available connectors and search relevant correspondence with this person, related emails, messages and chats, meeting transcripts, documents, and project records. Look for previous commitments, attempts to resolve the issue, disputed facts, and subsequent developments. Track dates so an old promise or disagreement is not mistaken for the current position. If access is unavailable, use what I supplied and offer help sharing the specific material that would matter most. Use actual exchanges to understand the recipient’s communication style: for example, whether concise requests or a fuller explanation have previously elicited useful responses. Treat any prediction of their reaction as an inference, not knowledge of their motives or personality. Ask what I want to achieve if that remains unclear. Be direct about consequential factual ambiguity and wait for clarification before asserting a disputed point as settled. ### 2. Separate the substance from the anger. Identify the facts, consequences, request, and boundaries worth retaining. Distinguish observations from assumptions about intention. Replace insults, sarcasm, exaggeration, and accusations of motive with specific descriptions of conduct and its effect. Preserve legitimate urgency and accountability; politeness does not require apologizing for raising the issue or giving up a necessary boundary. Offer to provide two versions, and provide both unless I prefer one: - Gentle and fully polite: make the concern and request easy to engage with, allowing room for clarification and repair. - Forceful and professional: state the issue, consequence, necessary action, and justified deadline or boundary plainly, without anger or personal attack. Keep the underlying facts consistent. Do not introduce threats, concessions, admissions, or new commitments I have not chosen. If a materially different request or boundary could be useful, explain it as an option and ask before treating it as my position. ### 3. Draft, check, and refine. Write complete emails, including a useful subject line where needed. Make the action sought unmistakable. Check names, chronology, quotations, deadlines, and claims against the available record. Read each version from the recipient’s perspective, looking for avoidable ambiguity or a sentence that undermines the intended outcome. Present the drafts and briefly explain their tonal difference. Ask which feels right or whether I want to combine them, and revise in response. If I do not choose yet, leave both ready for comparison without calling either my final choice. End with the usable draft or alternatives and any unresolved detail. Do not send the email as part of this activity. 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 an angry email into something sendable.
What the AI will do
- Investigate the issue’s history and relevant exchanges with the recipient, then rewrite your message without losing its substance.
- Offer a gentle version and a forceful professional version.
What you can provide
- The draft, thread, or a rough account of the issue; available connected correspondence can fill in context.
Where you'll take part
- Clarify the outcome you want and any disputed facts, then choose or combine the two tones.
What you'll get
You have a sendable email that addresses the issue clearly, in a tone you choose, with factual claims checked against the available record.
Activity context
Keep the force of your complaint. Lose the anger that makes it easier to dismiss.
For the user
Share the angry draft or describe what you want to say. The AI can look for relevant correspondence and records of the issue. You can compare a gentle version with a more forceful professional one, then refine the version that serves your purpose.
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 an angry email into something sendable. Preserve the issue and the outcome I need while removing anger that would distract from them.
1. Understand the issue, relationship, and intended outcome.
Read my draft and the surrounding thread, or build a draft from my account if I have not written one. Identify what happened, why it matters, what I want the recipient to do, and any deadline or relationship consideration already apparent.
Check available connectors and search relevant correspondence with this person, related emails, messages and chats, meeting transcripts, documents, and project records. Look for previous commitments, attempts to resolve the issue, disputed facts, and subsequent developments. Track dates so an old promise or disagreement is not mistaken for the current position. If access is unavailable, use what I supplied and offer help sharing the specific material that would matter most.
Use actual exchanges to understand the recipient’s communication style: for example, whether concise requests or a fuller explanation have previously elicited useful responses. Treat any prediction of their reaction as an inference, not knowledge of their motives or personality. Ask what I want to achieve if that remains unclear. Be direct about consequential factual ambiguity and wait for clarification before asserting a disputed point as settled.
2. Separate the substance from the anger.
Identify the facts, consequences, request, and boundaries worth retaining. Distinguish observations from assumptions about intention. Replace insults, sarcasm, exaggeration, and accusations of motive with specific descriptions of conduct and its effect. Preserve legitimate urgency and accountability; politeness does not require apologizing for raising the issue or giving up a necessary boundary.
Offer to provide two versions, and provide both unless I prefer one:
- Gentle and fully polite: make the concern and request easy to engage with, allowing room for clarification and repair.
- Forceful and professional: state the issue, consequence, necessary action, and justified deadline or boundary plainly, without anger or personal attack.
Keep the underlying facts consistent. Do not introduce threats, concessions, admissions, or new commitments I have not chosen. If a materially different request or boundary could be useful, explain it as an option and ask before treating it as my position.
3. Draft, check, and refine.
Write complete emails, including a useful subject line where needed. Make the action sought unmistakable. Check names, chronology, quotations, deadlines, and claims against the available record. Read each version from the recipient’s perspective, looking for avoidable ambiguity or a sentence that undermines the intended outcome.
Present the drafts and briefly explain their tonal difference. Ask which feels right or whether I want to combine them, and revise in response. If I do not choose yet, leave both ready for comparison without calling either my final choice. End with the usable draft or alternatives and any unresolved detail. Do not send the email as part of this activity.
Done when
You have a sendable email that addresses the issue clearly, in a tone you choose, with factual claims checked against the available record.
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.