Fix or retire the reports nobody reads.
Which of your recurring reports get people thinking, and which disappear into the void? Have AI look through your email and internal chat for evidence, then recommend what to keep, fix, or retire.
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
- Find recurring reports in accessible email, chat, or supplied material and trace discussion and later use.
- Recommend what to keep, improve, combine, or consider retiring, then develop the strongest supported change after your review.
What to have ready
- Your department or reporting period if needed to focus the search.
- Reports or related messages you already have, and a permitted access or export step if needed; the AI investigates the available routes.
Where you come in
- Review the strongest opportunity before the AI develops it.
- Add context the records may miss, such as a quiet report that drives a meeting, and correct the recommendation.
What you'll get
An evidence-backed assessment and a separate revised-report draft or retirement proposal where warranted, or a supported explanation that no change is needed; missing evidence stays explicit.
You're done when
You have an evidence-backed view of which reports appear useful and which deserve another look, with your corrections incorporated, and either a concrete revision or retirement proposal for the strongest candidate or a supported explanation of why no change is warranted.
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 email and internal office chat to find recurring reports that I or my department share with others in the organization. Do the searching and analysis yourself. Use context you already have; ask one question at a time if you need to establish my department or narrow the scope. ### 1. Establish access and the evidence available First inspect your available tools and connections and try searching the sources you can access. If access is missing or a search fails, investigate whether an available connection or setup option would enable it. Use accessible sources and any reports, messages, links, exports, or copied text I have supplied. Explain useful missing access and the specific step that needs my help; if it is necessary to proceed, ask whether I can enable it or provide the material another way, including any required administrator approval. Offer to walk me through a permitted export or upload. Continue useful analysis with the evidence available. State which sources and dates you could actually inspect. If this capability is unavailable at my company, explain how email and chat access could help you find recurring work, trace discussions, and identify what people use. Explain that read-only access can support this analysis without giving you permission to send or change messages. Offer to draft a letter to IT describing the access needed, the intended analysis, and the value it could provide. Describe the review as pending access or material only if no usable evidence is available and useful analysis cannot proceed. Otherwise, review the available evidence and explain how missing sources limit the findings. ### 2. Trace report use across editions - Using the accessible or supplied evidence, find the reports and trace what happens after they are shared, including later references and related conversations. - Look for substantive questions, interpretations, decisions, actions, or changes of mind. - Distinguish these from acknowledgments and emoji reactions. - Compare patterns across several editions where available. - Treat minimal response as a signal to investigate, not proof that nobody reads or uses a report. ### 3. Present the assessment and wait for your judgment Give me a concise assessment of which reports show evidence of usefulness and which attract little visible engagement. For each, link to supporting messages or identify the supplied source and date, explain what the evidence suggests, and recommend keeping, improving, combining, or considering retirement. Recommend concrete improvements where the evidence supports them, such as putting a repeatedly requested comparison at the top. Identify the strongest opportunity supported by the evidence and ask for my judgment on it. Wait for my response before developing the proposed change. Invite context you could not see, such as a quiet report driving a standing meeting. ### 4. Develop and check the supported change Incorporate my corrections, reconsider the recommendation, and draft a revised report or a short retirement proposal for the strongest candidate, as appropriate to my judgment and the evidence. For a revision, use the available report material and mark any missing inputs. For a retirement proposal, explain the evidence, any uses that need preserving, and the proposed change. If my corrections show that no change is warranted, deliver the corrected assessment and explain that conclusion rather than manufacture a proposal. Check the result against the source material and my corrections, and make clear what remains uncertain or unfinished. Do not send messages, change reporting schedules, or alter existing recurring reports; deliver the revision or proposal as a separate draft for me to use. 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
Fix or retire the reports nobody reads.
What the AI will do
- Find recurring reports in accessible email, chat, or supplied material and trace discussion and later use.
- Recommend what to keep, improve, combine, or consider retiring, then develop the strongest supported change after your review.
What you can provide
- Your department or reporting period if needed to focus the search.
- Reports or related messages you already have, and a permitted access or export step if needed; the AI investigates the available routes.
Where you'll take part
- Review the strongest opportunity before the AI develops it.
- Add context the records may miss, such as a quiet report that drives a meeting, and correct the recommendation.
What you'll get
An evidence-backed assessment and a separate revised-report draft or retirement proposal where warranted, or a supported explanation that no change is needed; missing evidence stays explicit.
Activity context
Which of your recurring reports get people thinking, and which disappear into the void? Have AI look through your email and internal chat for evidence, then recommend what to keep, fix, or retire.
For the user
Open your work AI and paste the prompt below. If you want to focus on a particular department or reporting period, say so. The AI will first try the email and chat access available in your setup and use any reports or messages you supply. You will review the findings and suggested change, add context it could not see, and have it develop the strongest candidate into a revised report or retirement proposal where warranted.
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 email and internal office chat to find recurring reports that I or my department share with others in the organization. Do the searching and analysis yourself. Use context you already have; ask one question at a time if you need to establish my department or narrow the scope.
1. Establish access and the evidence available
First inspect your available tools and connections and try searching the sources you can access. If access is missing or a search fails, investigate whether an available connection or setup option would enable it. Use accessible sources and any reports, messages, links, exports, or copied text I have supplied.
Explain useful missing access and the specific step that needs my help; if it is necessary to proceed, ask whether I can enable it or provide the material another way, including any required administrator approval. Offer to walk me through a permitted export or upload. Continue useful analysis with the evidence available. State which sources and dates you could actually inspect.
If this capability is unavailable at my company, explain how email and chat access could help you find recurring work, trace discussions, and identify what people use. Explain that read-only access can support this analysis without giving you permission to send or change messages. Offer to draft a letter to IT describing the access needed, the intended analysis, and the value it could provide.
Describe the review as pending access or material only if no usable evidence is available and useful analysis cannot proceed. Otherwise, review the available evidence and explain how missing sources limit the findings.
2. Trace report use across editions
- Using the accessible or supplied evidence, find the reports and trace what happens after they are shared, including later references and related conversations.
- Look for substantive questions, interpretations, decisions, actions, or changes of mind.
- Distinguish these from acknowledgments and emoji reactions.
- Compare patterns across several editions where available.
- Treat minimal response as a signal to investigate, not proof that nobody reads or uses a report.
3. Present the assessment and wait for your judgment
Give me a concise assessment of which reports show evidence of usefulness and which attract little visible engagement. For each, link to supporting messages or identify the supplied source and date, explain what the evidence suggests, and recommend keeping, improving, combining, or considering retirement. Recommend concrete improvements where the evidence supports them, such as putting a repeatedly requested comparison at the top.
Identify the strongest opportunity supported by the evidence and ask for my judgment on it. Wait for my response before developing the proposed change. Invite context you could not see, such as a quiet report driving a standing meeting.
4. Develop and check the supported change
Incorporate my corrections, reconsider the recommendation, and draft a revised report or a short retirement proposal for the strongest candidate, as appropriate to my judgment and the evidence. For a revision, use the available report material and mark any missing inputs. For a retirement proposal, explain the evidence, any uses that need preserving, and the proposed change.
If my corrections show that no change is warranted, deliver the corrected assessment and explain that conclusion rather than manufacture a proposal. Check the result against the source material and my corrections, and make clear what remains uncertain or unfinished. Do not send messages, change reporting schedules, or alter existing recurring reports; deliver the revision or proposal as a separate draft for me to use.
Done when
You have an evidence-backed view of which reports appear useful and which deserve another look, with your corrections incorporated, and either a concrete revision or retirement proposal for the strongest candidate or a supported explanation of why 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.
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.