Scour email and chat for your unique strengths.
Some strengths are so familiar to you that they barely register as skills: the encouraging email, the lone dissent that improves a decision, the gentle redirection that gets a project moving. Have AI look for what you actually contribute in the exchanges and outcomes around your work.
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
- Search messages you wrote, received, or were discussed in, and follow promising episodes into project records and results.
- Identify recurring abilities, ways of working, and interpersonal style, checking what others did afterward and where the pattern did not hold.
What to have ready
- Available email, chat, and project records, or a few complete exchanges and work examples to begin.
- Context about your role and contributions or outcomes that are missing from the record.
Where you come in
- Discuss specific episodes and correct how the AI has interpreted your contribution.
- Choose where you would like to use an evidenced strength more deliberately.
What you'll get
A sourced profile of distinctive contributions, with concrete examples, limits to the evidence, and specific opportunities to use them.
You're done when
You have discussed and corrected a sourced account of your recurring contributions and identified concrete occasions to use any strengths you choose. Observed style, demonstrated effects, and tentative interpretations are distinguished; limited material produces a provisional profile.
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 see distinctive strengths in my actual work by examining email and chat, then tracing promising examples into project outcomes. Include abilities, ways of working, and interpersonal style. Produce a profile I can recognize, question, and use; do not turn this into generic praise or a personality verdict. ### 1. Find the right evidence Inspect and try access to messages I wrote, messages addressed to me, and accessible exchanges discussing my contributions. Include email, company chat, and other relevant messages such as WhatsApp where available. Search using my name, role, projects, collaborators, deliverable names, and useful phrases found in the first results. Follow references into meeting transcripts, project documents, decisions, feedback, and completed work to understand what those exchanges were about and what happened afterward. Establish my current role and responsibilities from accessible records and what I have supplied. Choose a useful period broad enough to include several projects or situations; show its dates and coverage. Ask a focused question if you cannot establish who I am or what work belongs in scope. When records are missing, investigate available connection and export routes before asking me to gather examples. Explain what access would enable and offer an IT request if helpful. With no workable connection, welcome a few pasted or exported full exchanges and related work; build a provisional account from those. Ask for missing context only when it affects interpretation. Recollections can explain an episode, but label them separately from contemporary evidence. Do not describe a handful of selected successes as a comprehensive assessment. ### 2. Investigate episodes, not just adjectives Look broadly for contributions such as explaining a difficult idea, noticing an overlooked question, encouraging someone, raising the only dissenting view, gently redirecting a project, connecting people or ideas, or helping a group move forward. These examples are starting points; let the record reveal other kinds of strength. For each promising episode, preserve the exchange and reconstruct: - The situation before my contribution: the task, disagreement, confusion, or opportunity. - What I actually said, did, or produced, with a short excerpt or precise reference. - Who was involved and what their roles and expressed needs were, using correspondence, meeting participants, and project records. - How others responded and what they subsequently did. - What changed in the work, decision, or relationship, where the record supports it. - Other contributors, alternative explanations, and what remains unknown. A thank-you or compliment is evidence of a reaction. Follow it into actions and outcomes before claiming impact. An encouraging style can be well supported even when its effects are unknown. Distinguish what I contributed from the collective result. Read complete exchanges rather than searching only for praise words. Include routine work, difficult interactions, and cases where a promising contribution was ignored or did not help. Compare similar episodes across people and projects. Distinguish recurring behavior from one standout event and a distinctive contribution from something the available evidence cannot compare with other people's work. If the corpus is large, divide by complete project or relationship histories. Give agents the same episode questions and require source references, dates, excerpts, counterexamples, and coverage. Preserve enough preceding and subsequent context to interpret each exchange. Reconcile repeated episodes and conflicting interpretations yourself. If delegation is unavailable, use bounded sequential passes and keep a coverage record. ### 3. Build and discuss the profile Select a small set of the best-supported patterns. Describe each in concrete language: what I do, in which circumstances it seems useful, and how it may help. Support it with more than one episode where possible and explicitly label single-example candidates. Separate observed style, evidence of an ability, others' reported appreciation, and demonstrated consequence; do not collapse them into a confidence score. Show me the strongest examples and the uncertainties. Ask what fits or misses my experience, and wait before presenting the profile as settled. Explore any disputed interpretation against the record. Invite examples of unrecorded work and counterexamples, without making me defend myself against an assessment. Revise the profile to reflect what the evidence and our discussion can support. If something is a desired future strength rather than an observed one, say so. ### 4. Find useful occasions to apply it Search accessible upcoming project plans, calendar events, open issues, and relevant exchanges for situations where the supported contributions might help. Use actual participants' roles, expressed concerns, and prior responses to explain the fit. Label any predicted reaction as an inference, not their judgment. For the most useful opportunities, specify the situation, the contribution I could make, why this strength fits, and a concrete first action. For example, an evidenced ability to redirect a stalled discussion may fit an actual project review; frequent encouragement may suggest a specific moment to acknowledge work. Do not prescribe the example if the evidence points elsewhere. Ask which opportunities I want to use and incorporate my choices. Deliver a concise profile with the key source-linked episodes, contrary cases or limits, and the selected practical applications. Let the record support a modest or mixed finding. Do not send messages to colleagues or represent a contribution I have not chosen as my commitment. 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
Scour email and chat for your unique strengths.
What the AI will do
- Search messages you wrote, received, or were discussed in, and follow promising episodes into project records and results.
- Identify recurring abilities, ways of working, and interpersonal style, checking what others did afterward and where the pattern did not hold.
What you can provide
- Available email, chat, and project records, or a few complete exchanges and work examples to begin.
- Context about your role and contributions or outcomes that are missing from the record.
Where you'll take part
- Discuss specific episodes and correct how the AI has interpreted your contribution.
- Choose where you would like to use an evidenced strength more deliberately.
What you'll get
A sourced profile of distinctive contributions, with concrete examples, limits to the evidence, and specific opportunities to use them.
Activity context
Some strengths are so familiar to you that they barely register as skills: the encouraging email, the lone dissent that improves a decision, the gentle redirection that gets a project moving. Have AI look for what you actually contribute in the exchanges and outcomes around your work.
For the user
Use the prompt below with the AI that can reach your work records. It will look for evidence of how you help work and people move forward. You will discuss its examples, correct its conclusions, and identify occasions where a strength could be especially useful.
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 see distinctive strengths in my actual work by examining email and chat, then tracing promising examples into project outcomes. Include abilities, ways of working, and interpersonal style. Produce a profile I can recognize, question, and use; do not turn this into generic praise or a personality verdict.
1. Find the right evidence
Inspect and try access to messages I wrote, messages addressed to me, and accessible exchanges discussing my contributions. Include email, company chat, and other relevant messages such as WhatsApp where available. Search using my name, role, projects, collaborators, deliverable names, and useful phrases found in the first results. Follow references into meeting transcripts, project documents, decisions, feedback, and completed work to understand what those exchanges were about and what happened afterward.
Establish my current role and responsibilities from accessible records and what I have supplied. Choose a useful period broad enough to include several projects or situations; show its dates and coverage. Ask a focused question if you cannot establish who I am or what work belongs in scope.
When records are missing, investigate available connection and export routes before asking me to gather examples. Explain what access would enable and offer an IT request if helpful. With no workable connection, welcome a few pasted or exported full exchanges and related work; build a provisional account from those. Ask for missing context only when it affects interpretation. Recollections can explain an episode, but label them separately from contemporary evidence. Do not describe a handful of selected successes as a comprehensive assessment.
2. Investigate episodes, not just adjectives
Look broadly for contributions such as explaining a difficult idea, noticing an overlooked question, encouraging someone, raising the only dissenting view, gently redirecting a project, connecting people or ideas, or helping a group move forward. These examples are starting points; let the record reveal other kinds of strength.
For each promising episode, preserve the exchange and reconstruct:
- The situation before my contribution: the task, disagreement, confusion, or opportunity.
- What I actually said, did, or produced, with a short excerpt or precise reference.
- Who was involved and what their roles and expressed needs were, using correspondence, meeting participants, and project records.
- How others responded and what they subsequently did.
- What changed in the work, decision, or relationship, where the record supports it.
- Other contributors, alternative explanations, and what remains unknown.
A thank-you or compliment is evidence of a reaction. Follow it into actions and outcomes before claiming impact. An encouraging style can be well supported even when its effects are unknown. Distinguish what I contributed from the collective result.
Read complete exchanges rather than searching only for praise words. Include routine work, difficult interactions, and cases where a promising contribution was ignored or did not help. Compare similar episodes across people and projects. Distinguish recurring behavior from one standout event and a distinctive contribution from something the available evidence cannot compare with other people's work.
If the corpus is large, divide by complete project or relationship histories. Give agents the same episode questions and require source references, dates, excerpts, counterexamples, and coverage. Preserve enough preceding and subsequent context to interpret each exchange. Reconcile repeated episodes and conflicting interpretations yourself. If delegation is unavailable, use bounded sequential passes and keep a coverage record.
3. Build and discuss the profile
Select a small set of the best-supported patterns. Describe each in concrete language: what I do, in which circumstances it seems useful, and how it may help. Support it with more than one episode where possible and explicitly label single-example candidates. Separate observed style, evidence of an ability, others' reported appreciation, and demonstrated consequence; do not collapse them into a confidence score.
Show me the strongest examples and the uncertainties. Ask what fits or misses my experience, and wait before presenting the profile as settled. Explore any disputed interpretation against the record. Invite examples of unrecorded work and counterexamples, without making me defend myself against an assessment. Revise the profile to reflect what the evidence and our discussion can support. If something is a desired future strength rather than an observed one, say so.
4. Find useful occasions to apply it
Search accessible upcoming project plans, calendar events, open issues, and relevant exchanges for situations where the supported contributions might help. Use actual participants' roles, expressed concerns, and prior responses to explain the fit. Label any predicted reaction as an inference, not their judgment.
For the most useful opportunities, specify the situation, the contribution I could make, why this strength fits, and a concrete first action. For example, an evidenced ability to redirect a stalled discussion may fit an actual project review; frequent encouragement may suggest a specific moment to acknowledge work. Do not prescribe the example if the evidence points elsewhere. Ask which opportunities I want to use and incorporate my choices.
Deliver a concise profile with the key source-linked episodes, contrary cases or limits, and the selected practical applications. Let the record support a modest or mixed finding. Do not send messages to colleagues or represent a contribution I have not chosen as my commitment.
Done when
You have discussed and corrected a sourced account of your recurring contributions and identified concrete occasions to use any strengths you choose. Observed style, demonstrated effects, and tentative interpretations are distinguished; limited material produces a provisional profile.
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.