Reveal your true priorities.
If someone saw only your calendar, messages, and work, what would they think your job was? Have AI write the job description your working life suggests, then compare it with the job you’re meant to be doing.
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 the pattern in your time, conversations, and output, or build a picture from an interview about recent work.
- Reveal the job title and description that this evidence suggests before asking about your official role.
- Use your corrections to compare that portrait with your intended responsibilities and explore changes worth making.
What to have ready
- Available calendar records, messages, documents, or rough notes about recent work. The AI can help you export and share them.
- Save your official title and job description until after the AI reveals its portrait.
Where you come in
- Fill gaps about concrete recent work, then respond to the inferred role and share your formal responsibilities.
- Correct the comparison and decide whether a change is worth pursuing; if you choose one, work out a practical first step with the AI.
What you'll get
You’ll have a job portrait inferred from your work, a corrected comparison with your intended role, and a practical first change or an informed decision to keep things as they are, with evidence gaps made clear.
You're done when
You have a job title and description inferred from your work and a comparison with your intended role that incorporates your corrections. You have either a practical first change you want to make or an informed decision that no change is warranted, with its basis and any remaining evidence gaps made clear.
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 discover what my working life says my job really is. Infer it from what I spend time on, discuss, and produce. First show me the role that emerges; only afterward ask about my official job. Ask one focused question at a time when you need my input. ### 1. Gather a picture of my work without starting from my title. Check and try your available access to my calendar, email, company chat, and documents I have written or substantially contributed to. Use recent weeks as a starting point, and look far enough back to include major projects and recurring responsibilities where possible. Tell me which sources and period you can examine. If you need to establish which account or person is mine, ask for that without asking for my title or job description. If access is missing, inspect available connection options and explain any specific action I would need to take. Welcome copied messages, calendar exports, documents, or rough notes. Offer to walk me through how to export these materials and make them available to you. If company access needs enabling, explain what read-only access would make possible and offer to draft a request to IT. Continue with the material we can use. If the records are unavailable or incomplete, interview me about concrete recent work. Start with what I did in the last few days, then explore the last couple of weeks and any major projects. Ask what took time, what I made or delivered, what people kept asking me about, and what important work happened outside meetings or messages. Follow up for examples and approximate time commitments. Build the work history yourself from my answers; don’t require me to reconstruct months of activity or prepare a report. ### 2. Infer the job from the work. Read calendar entries, relevant message threads, and the substance of my documents. Group the work by what it accomplishes, who it serves, and the responsibility I appear to carry. Compare three signals: - where my time goes, - what I repeatedly discuss, - and what I produce. Look for the underlying role connecting them. A person who spends the week resolving disputes, reviewing proposals, and unblocking decisions may be doing something different from what the meeting titles suggest. Use calendar duration as an estimate of scheduled time, checking attendance or actual effort where the record permits. Keep message frequency and output separate from hours worked; account for duplicate threads, coauthored material, and major work that leaves few messages. Seek evidence that complicates your first interpretation. Distinguish sustained responsibilities from an unusual week or temporary crisis. If that distinction would change the result, ask about it without requesting my formal role. Keep my official title and job description out of the inference. If separate agents are available, give a fresh agent the relevant work evidence and this analysis task, omitting explicit titles, formal job descriptions, and your own proposed interpretation. Have it infer the role and support its reading with examples. Otherwise make your inference directly from the work, setting aside any title you already know. Don’t claim an independent or title-blind analysis if the setup did not provide one. ### 3. Reveal the role that emerges. Present a substantive overview of what my job appears to be, give that role a title, and write a short job description. Include its purpose, principal responsibilities, who relies on it, and the outputs it appears to deliver. A little playfulness in the title is welcome, but the description should be serious enough to recognize and use. Support the portrait with concrete examples from my time, communications, and output, using dates and source links or identifying details where available. Label interview evidence as my account. Explain any important gaps in the picture. Describe the priorities expressed by my work without assuming they are what I personally value or freely chose. Ask how close this is to my actual job, and invite me to share my official role and any missing context. Stop and wait for my answer before making the comparison. ### 4. Compare, revise, and discuss changes. Use my response to compare the inferred role with my intended responsibilities. If I haven’t made those responsibilities clear, ask before recommending changes. Identify which discrepancies reflect missing evidence, which reflect temporary demands, and which seem to be enduring differences between my actual and intended work. Revise your portrait when new information changes it, explaining what changed your view. Discuss what I might do to bring my work, calendar, and conversations closer to the role I should be doing. Tie suggestions to specific discrepancies: protect time for an underrepresented responsibility, clarify ownership of work I’ve absorbed, change a recurring meeting, or redirect a recurring discussion. Treat these as examples and develop the changes that fit my situation. Leave room for the possibility that the formal role needs updating to recognize valuable work I already do. Ask whether any change feels worth pursuing and wait for my response. If I select one, refine it with me into a practical first step. If the corrected portrait and comparison support keeping things as they are and I agree, record that informed decision and its basis. Keep unresolved evidence gaps explicit rather than treating them as proof that no change is warranted. 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
Reveal your true priorities.
What the AI will do
- Read the pattern in your time, conversations, and output, or build a picture from an interview about recent work.
- Reveal the job title and description that this evidence suggests before asking about your official role.
- Use your corrections to compare that portrait with your intended responsibilities and explore changes worth making.
What you can provide
- Available calendar records, messages, documents, or rough notes about recent work. The AI can help you export and share them.
- Save your official title and job description until after the AI reveals its portrait.
Where you'll take part
- Fill gaps about concrete recent work, then respond to the inferred role and share your formal responsibilities.
- Correct the comparison and decide whether a change is worth pursuing; if you choose one, work out a practical first step with the AI.
What you'll get
You’ll have a job portrait inferred from your work, a corrected comparison with your intended role, and a practical first change or an informed decision to keep things as they are, with evidence gaps made clear.
Activity context
If someone saw only your calendar, messages, and work, what would they think your job was? Have AI write the job description your working life suggests, then compare it with the job you’re meant to be doing.
For the user
Paste the prompt below into your work AI. Let it examine your calendar, email, company chat, and documents you’ve produced, or share whatever you have. If those aren’t available, it will interview you about the last few days or weeks. Save your official title and job description for the reveal.
You’ll read its account of your job, fill in anything it missed, and discuss changes that could bring your daily work closer to your intended role.
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 discover what my working life says my job really is. Infer it from what I spend time on, discuss, and produce. First show me the role that emerges; only afterward ask about my official job. Ask one focused question at a time when you need my input.
1. Gather a picture of my work without starting from my title.
Check and try your available access to my calendar, email, company chat, and documents I have written or substantially contributed to. Use recent weeks as a starting point, and look far enough back to include major projects and recurring responsibilities where possible. Tell me which sources and period you can examine. If you need to establish which account or person is mine, ask for that without asking for my title or job description.
If access is missing, inspect available connection options and explain any specific action I would need to take. Welcome copied messages, calendar exports, documents, or rough notes. Offer to walk me through how to export these materials and make them available to you. If company access needs enabling, explain what read-only access would make possible and offer to draft a request to IT. Continue with the material we can use.
If the records are unavailable or incomplete, interview me about concrete recent work. Start with what I did in the last few days, then explore the last couple of weeks and any major projects. Ask what took time, what I made or delivered, what people kept asking me about, and what important work happened outside meetings or messages. Follow up for examples and approximate time commitments. Build the work history yourself from my answers; don’t require me to reconstruct months of activity or prepare a report.
2. Infer the job from the work.
Read calendar entries, relevant message threads, and the substance of my documents. Group the work by what it accomplishes, who it serves, and the responsibility I appear to carry. Compare three signals:
-
where my time goes,
-
what I repeatedly discuss,
-
and what I produce.
Look for the underlying role connecting them. A person who spends the week resolving disputes, reviewing proposals, and unblocking decisions may be doing something different from what the meeting titles suggest.
Use calendar duration as an estimate of scheduled time, checking attendance or actual effort where the record permits. Keep message frequency and output separate from hours worked; account for duplicate threads, coauthored material, and major work that leaves few messages.
Seek evidence that complicates your first interpretation. Distinguish sustained responsibilities from an unusual week or temporary crisis. If that distinction would change the result, ask about it without requesting my formal role.
Keep my official title and job description out of the inference. If separate agents are available, give a fresh agent the relevant work evidence and this analysis task, omitting explicit titles, formal job descriptions, and your own proposed interpretation. Have it infer the role and support its reading with examples. Otherwise make your inference directly from the work, setting aside any title you already know. Don’t claim an independent or title-blind analysis if the setup did not provide one.
3. Reveal the role that emerges.
Present a substantive overview of what my job appears to be, give that role a title, and write a short job description. Include its purpose, principal responsibilities, who relies on it, and the outputs it appears to deliver. A little playfulness in the title is welcome, but the description should be serious enough to recognize and use.
Support the portrait with concrete examples from my time, communications, and output, using dates and source links or identifying details where available. Label interview evidence as my account. Explain any important gaps in the picture. Describe the priorities expressed by my work without assuming they are what I personally value or freely chose.
Ask how close this is to my actual job, and invite me to share my official role and any missing context. Stop and wait for my answer before making the comparison.
4. Compare, revise, and discuss changes.
Use my response to compare the inferred role with my intended responsibilities. If I haven’t made those responsibilities clear, ask before recommending changes. Identify which discrepancies reflect missing evidence, which reflect temporary demands, and which seem to be enduring differences between my actual and intended work. Revise your portrait when new information changes it, explaining what changed your view.
Discuss what I might do to bring my work, calendar, and conversations closer to the role I should be doing. Tie suggestions to specific discrepancies: protect time for an underrepresented responsibility, clarify ownership of work I’ve absorbed, change a recurring meeting, or redirect a recurring discussion. Treat these as examples and develop the changes that fit my situation. Leave room for the possibility that the formal role needs updating to recognize valuable work I already do.
Ask whether any change feels worth pursuing and wait for my response.
If I select one, refine it with me into a practical first step.
If the corrected portrait and comparison support keeping things as they are and I agree, record that informed decision and its basis. Keep unresolved evidence gaps explicit rather than treating them as proof that no change is warranted.
Done when
You have a job title and description inferred from your work and a comparison with your intended role that incorporates your corrections. You have either a practical first change you want to make or an informed decision that no change is warranted, with its basis and any remaining evidence gaps made clear.
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.