Find your communication blind spots in sent emails.
Your sent emails may reveal habits you cannot see while writing them. Have AI find the recurring friction, show you examples, and suggest ways to make the same point more clearly.
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 sent emails in their thread context to find recurring communication friction and show better alternatives.
- Turn agreed improvements into a personal email style guide, with an optional tool to screen and improve drafts.
What to have ready
- Access to sent mail or a collection through a permitted route; the AI checks connections and helps with export if needed.
- Context that helps explain the messages and what you intended.
Where you come in
- Review the themes and examples, correct the interpretation, and choose which habits to improve.
- Decide whether to accept the follow-on tool and complete any required installation; sending remains your decision.
What you'll get
Examples from your emails, clearer rewrites, and a reusable style guide; if you choose the tool, a tested draft-improvement tool or an exact account of installation or access still needed.
You're done when
You have communication habits you recognize, examples from your own emails, clearer alternatives, and a reusable personal email style guide. If you choose the follow-on tool, you also have a tested way to screen and improve drafts, or a specific explanation of the installation or access still needed.
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. Review my sent emails for communication blind spots and show me how to improve them. Do the investigation yourself wherever you have access. Ask one focused question at a time when you need my input. ### 1. Get a useful collection of my sent emails. Check your available connections and try to read sent mail. Identify my email service from the available context; ask me if you cannot establish it. If access is missing, investigate connection options first. If I need to provide emails, check current instructions for my service and give me direct steps for finding a collection of sent messages, downloading or exporting them in a format you can read, and bringing them into this chat. If export is unavailable, help me use another permitted route, such as copying a selection. Explain what read-only access would enable and offer to draft an IT request if my organization needs to enable it. Choose a manageable initial collection spanning different recipients, purposes, and dates. Tell me what you can examine. Read the messages themselves, with enough thread context to understand what I was responding to and what I wanted to happen. Distinguish my newly written text from quoted replies and signatures. Retrieve more or ask for specific additional material if the collection is too narrow to establish recurring habits. ### 2. Find recurring communication problems. Look for ways my emails could work better for their recipients. Possibilities include being too short to supply needed context, too long for the purpose, unclear about the request or next step, opaque, brusque, or so elaborately polite that the point gets lost. These are examples, not an exhaustive checklist. Judge each message in context: brevity may be helpful in an established exchange and confusing in a new request. - Group repeated problems into themes. - Check each theme across separate emails and look for context that might explain the wording. - Distinguish what the email says from how you think it might be received. - Claim a recipient's actual reaction only when their response supplies evidence. ### 3. Show me the patterns and better alternatives. - For each supported theme, explain the habit and why it could create friction. - Give two or three examples from actual emails, with dates and links or another way to locate them. - Show the relevant original wording alongside a better version conveying the same meaning. - Preserve facts, commitments, intended tone, and the relationship. - Do not invent deadlines or promises to make a rewrite more decisive. - If only one example supports a concern, describe it as a possibility rather than a recurring pattern. Present the strongest themes first. Ask whether I agree with your reading and which habits, if any, I want to improve. Wait for my response, then revise your conclusions and examples accordingly. Then create a personal email style guide based on the improvements we agree on. Include clear writing guidance and before-and-after examples that address my blind spots while preserving my voice. Give me the guide in a form I can reuse when drafting or reviewing emails. ### 4. Offer to turn the findings into an email tool. Offer to build a tool that screens my drafts for the agreed blind spots and improves them automatically. Use what you now know about my email service, connections, and available tools to investigate a feasible implementation. Explain where it would operate, how it would receive drafts, and how improved text would return to my email workflow. Wait for me to accept the offer before building. If I accept, inspect the relevant capabilities and current documentation, resolve essential setup questions, then build and test the tool against example drafts. Check that it catches the agreed habits and preserves my meaning. Automatic improvement should edit drafts; sending remains my decision. If I must install something, produce the installable artifact where possible, guide me through installation, and verify it works. If enterprise policy or unavailable access prevents this, establish the actual restriction, explain what must change, and offer a concrete request for the relevant administrator. Distinguish a tested tool from an artifact awaiting installation or an access request. 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
Find your communication blind spots in sent emails.
What the AI will do
- Read sent emails in their thread context to find recurring communication friction and show better alternatives.
- Turn agreed improvements into a personal email style guide, with an optional tool to screen and improve drafts.
What you can provide
- Access to sent mail or a collection through a permitted route; the AI checks connections and helps with export if needed.
- Context that helps explain the messages and what you intended.
Where you'll take part
- Review the themes and examples, correct the interpretation, and choose which habits to improve.
- Decide whether to accept the follow-on tool and complete any required installation; sending remains your decision.
What you'll get
Examples from your emails, clearer rewrites, and a reusable style guide; if you choose the tool, a tested draft-improvement tool or an exact account of installation or access still needed.
Activity context
Your sent emails may reveal habits you cannot see while writing them. Have AI find the recurring friction, show you examples, and suggest ways to make the same point more clearly.
For the user
Paste the prompt below into your work AI. It will check whether it can read your sent emails and help you provide a useful sample if needed.
As you work together, you’ll review the patterns and before-and-after examples, correct any missing context, and decide which habits you want to improve. The AI will turn the agreed improvements into a personal email style guide. You can also choose to have it build a tool that screens and improves your drafts.
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
Review my sent emails for communication blind spots and show me how to improve them. Do the investigation yourself wherever you have access. Ask one focused question at a time when you need my input.
1. Get a useful collection of my sent emails.
Check your available connections and try to read sent mail. Identify my email service from the available context; ask me if you cannot establish it. If access is missing, investigate connection options first. If I need to provide emails, check current instructions for my service and give me direct steps for finding a collection of sent messages, downloading or exporting them in a format you can read, and bringing them into this chat.
If export is unavailable, help me use another permitted route, such as copying a selection. Explain what read-only access would enable and offer to draft an IT request if my organization needs to enable it.
Choose a manageable initial collection spanning different recipients, purposes, and dates. Tell me what you can examine. Read the messages themselves, with enough thread context to understand what I was responding to and what I wanted to happen. Distinguish my newly written text from quoted replies and signatures. Retrieve more or ask for specific additional material if the collection is too narrow to establish recurring habits.
2. Find recurring communication problems.
Look for ways my emails could work better for their recipients. Possibilities include being too short to supply needed context, too long for the purpose, unclear about the request or next step, opaque, brusque, or so elaborately polite that the point gets lost. These are examples, not an exhaustive checklist. Judge each message in context: brevity may be helpful in an established exchange and confusing in a new request.
- Group repeated problems into themes.
- Check each theme across separate emails and look for context that might explain the wording.
- Distinguish what the email says from how you think it might be received.
- Claim a recipient's actual reaction only when their response supplies evidence.
3. Show me the patterns and better alternatives.
- For each supported theme, explain the habit and why it could create friction.
- Give two or three examples from actual emails, with dates and links or another way to locate them.
- Show the relevant original wording alongside a better version conveying the same meaning.
- Preserve facts, commitments, intended tone, and the relationship.
- Do not invent deadlines or promises to make a rewrite more decisive.
- If only one example supports a concern, describe it as a possibility rather than a recurring pattern.
Present the strongest themes first. Ask whether I agree with your reading and which habits, if any, I want to improve. Wait for my response, then revise your conclusions and examples accordingly. Then create a personal email style guide based on the improvements we agree on. Include clear writing guidance and before-and-after examples that address my blind spots while preserving my voice.
Give me the guide in a form I can reuse when drafting or reviewing emails.
4. Offer to turn the findings into an email tool.
Offer to build a tool that screens my drafts for the agreed blind spots and improves them automatically. Use what you now know about my email service, connections, and available tools to investigate a feasible implementation. Explain where it would operate, how it would receive drafts, and how improved text would return to my email workflow. Wait for me to accept the offer before building.
If I accept, inspect the relevant capabilities and current documentation, resolve essential setup questions, then build and test the tool against example drafts. Check that it catches the agreed habits and preserves my meaning. Automatic improvement should edit drafts; sending remains my decision. If I must install something, produce the installable artifact where possible, guide me through installation, and verify it works.
If enterprise policy or unavailable access prevents this, establish the actual restriction, explain what must change, and offer a concrete request for the relevant administrator. Distinguish a tested tool from an artifact awaiting installation or an access request.
Done when
You have communication habits you recognize, examples from your own emails, clearer alternatives, and a reusable personal email style guide. If you choose the follow-on tool, you also have a tested way to screen and improve drafts, or a specific explanation of the installation or access still needed.
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.