Find your department’s most consequential work.
Which part of your department’s work makes the biggest difference to everyone else? Enthusiastic feedback is a useful starting point. Follow it into what people actually do with your team's work, then compare that with the quiet contributions others depend on and the company's strategy.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigate company strategy, your team’s core work, and how people outside the team respond to and use its outputs.
- Trace promising contributions into decisions and results, then compare their consequence and effort with you.
What to have ready
- Context about your department and available plans, deliverables, feedback, operating records, or permitted access.
- Your knowledge of which work gets feedback, which gets enthusiastic feedback, and what other teams depend on.
Where you come in
- Discuss the team’s purpose and the feedback it receives, and explain contributions that may be quiet or invisible in the records.
- Review the strongest findings and choose concrete ways to support more of the consequential work.
What you'll get
An evidence-based account of the team’s largest apparent contributions outside itself and practical ways to strengthen them, with unresolved dependencies and impact claims kept visible.
You're done when
You have discussed an evidence-based account of the department’s most consequential contributions outside itself and selected any practical ways to strengthen them. The result accounts for enthusiastic feedback, actual use, quiet dependencies, strategy, and effort; unsupported impact claims remain unresolved rather than becoming a ranking.
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 find my department's most consequential work, especially its impact on people outside the team. Investigate actual use and results alongside a conversation with me about our work and the feedback it receives. Carry this through to supported findings and concrete ways to strengthen the best contributions. ### 1. Understand the team, strategy, and evidence Establish the company, department, responsibilities, and useful time period from what I have supplied and accessible records; ask a focused question if essential context is missing. Inspect and try access to current strategy and operating plans, the team's plans and deliverables, internal customer conversations, email replies, chat threads including other relevant messages where accessible, meeting transcripts, and operating evidence. Search using department names, projects, deliverables, stakeholders, and terms found in the initial records. Use strategy documents and leadership communications to establish intended company outcomes and current priorities, tracking which later decisions amend earlier ones. Use the team's actual plans and outputs to understand its core work. Use correspondence, meeting invitations, participant lists, and role records to identify who outside the team receives or depends on that work and what those people say they need. If useful sources are missing, investigate connections and export options before asking me to assemble material. Explain what access would enable and offer an IT request when helpful. Work from rough documents, complete feedback exchanges, or an interview if access cannot be enabled. State early when limited evidence means this will be a provisional assessment rather than a comprehensive account of the department. Summarize the team's purpose, main outputs, strategy connection, and likely outside users. Discuss these with me and resolve material misunderstandings before comparing the work's consequence. ### 2. Use the conversation to find promising leads Ask which work gets the most feedback and which gets the most enthusiastic feedback. Build on examples already found; ask one focused question at a time and wait when the answer determines the next investigation. Explore who gives that feedback, what they appreciated, and what they subsequently did. Ask about less visible work people rely on even when they rarely acknowledge it. Use this conversation to develop leads, not to declare a winner. Preserve my interpretation as my account and follow it into the records. Positive feedback may concern convenience, responsiveness, a better decision, a problem avoided, or a material operating result; find out which applies. Read negative feedback and requests for more help too, since they can reveal an important dependency or unmet need. ### 3. Follow outputs beyond the department Create a manageable inventory of the team's main work over the selected period, including quiet essential work as well as celebrated outputs. For promising contributions, trace a complete chain: - What the team did or delivered, when, and for whom. - The outside team's need, decision, or problem, using its own expressed concerns and records. - What feedback came back, from whom, and what it specifically referred to. - How the recipient actually used the work: a decision changed, work enabled, time released, an obstacle removed, or another supported consequence. - What happened afterward, and how directly the evidence connects it to the team's contribution. - The team's effort, other contributors, dependencies, contrary cases, and unresolved questions. Follow reply threads, later meetings, document references, project actions, and operating results. Distinguish praise from use, use from consequence, and a contribution to a result from sole causation. Missing thank-you emails do not establish low value. Look for repeated reliance on uncelebrated work and evidence of what happened when an input was delayed or absent; do not invent the counterfactual benefit of preventing a problem. For a broad department, divide investigation by outside stakeholder group or complete workstream. Give each agent the shared strategy and purpose, bounded source set, chain above, and instructions to return dated references, gaps, and competing explanations. Maintain coverage of work and recipients. Reconcile overlapping outputs and downstream results yourself so several groups do not each claim the same benefit. If agents are unavailable, perform sequential bounded passes. ### 4. Compare the contributions with me Present a short set of the strongest candidates. For each, show what it enables outside the team, the evidence, whose work benefits, its connection to strategy, and approximate effort where known. Label effort estimates and distinguish elapsed time from person-hours. Do not combine unlike benefits into a spurious numerical ranking. Explain why a contribution appears consequential and what could change that judgment. Include a quiet essential contribution when the evidence supports it. Where enthusiastic feedback and apparent strategic consequence point to different work, make that difference a topic for discussion. Ask me about missing dependencies, unrecorded use, and whether the comparison matches the team's responsibilities. Follow important new leads, revise the account, and leave disputed impact claims explicit. A smaller supported finding is more useful than a confident ranking the records cannot sustain. ### 5. Develop ways to support more of the valuable work For the best-supported contributions, propose concrete ways to strengthen or extend them: improve the part recipients actually use, deliver it at a more useful moment, remove an evidenced bottleneck, make an effective practice repeatable, or serve another group with the same demonstrated need. Let the findings determine the proposals. Explain for each proposal the intended benefit, evidence behind it, effort or dependency, and a small test with an observable result. Ask which changes I want to pursue and wait before recording them as my decisions. Keep any unresolved stakeholder validation visible; a proposed conversation is not feedback you have obtained. Deliver a concise account of where the department appears to make its largest contribution outside itself, backed by source-linked examples, plus the selected ways to support more of it. Include the scope examined and consequential unknowns. Do not contact colleagues, reallocate work, or announce changes as part of this assessment unless I ask for that execution. 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 department’s most consequential work.
What the AI will do
- Investigate company strategy, your team’s core work, and how people outside the team respond to and use its outputs.
- Trace promising contributions into decisions and results, then compare their consequence and effort with you.
What you can provide
- Context about your department and available plans, deliverables, feedback, operating records, or permitted access.
- Your knowledge of which work gets feedback, which gets enthusiastic feedback, and what other teams depend on.
Where you'll take part
- Discuss the team’s purpose and the feedback it receives, and explain contributions that may be quiet or invisible in the records.
- Review the strongest findings and choose concrete ways to support more of the consequential work.
What you'll get
An evidence-based account of the team’s largest apparent contributions outside itself and practical ways to strengthen them, with unresolved dependencies and impact claims kept visible.
Activity context
Which part of your department’s work makes the biggest difference to everyone else? Enthusiastic feedback is a useful starting point. Follow it into what people actually do with your team's work, then compare that with the quiet contributions others depend on and the company's strategy.
For the user
Use the prompt below to investigate your department’s contribution. Expect a conversation alongside the AI’s source work: you know which responses mattered, what praise misses, and how the team serves the firm. The AI will follow those leads and produce a concrete account you can use.
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 find my department's most consequential work, especially its impact on people outside the team. Investigate actual use and results alongside a conversation with me about our work and the feedback it receives. Carry this through to supported findings and concrete ways to strengthen the best contributions.
1. Understand the team, strategy, and evidence
Establish the company, department, responsibilities, and useful time period from what I have supplied and accessible records; ask a focused question if essential context is missing. Inspect and try access to current strategy and operating plans, the team's plans and deliverables, internal customer conversations, email replies, chat threads including other relevant messages where accessible, meeting transcripts, and operating evidence.
Search using department names, projects, deliverables, stakeholders, and terms found in the initial records. Use strategy documents and leadership communications to establish intended company outcomes and current priorities, tracking which later decisions amend earlier ones. Use the team's actual plans and outputs to understand its core work. Use correspondence, meeting invitations, participant lists, and role records to identify who outside the team receives or depends on that work and what those people say they need.
If useful sources are missing, investigate connections and export options before asking me to assemble material. Explain what access would enable and offer an IT request when helpful. Work from rough documents, complete feedback exchanges, or an interview if access cannot be enabled. State early when limited evidence means this will be a provisional assessment rather than a comprehensive account of the department.
Summarize the team's purpose, main outputs, strategy connection, and likely outside users. Discuss these with me and resolve material misunderstandings before comparing the work's consequence.
2. Use the conversation to find promising leads
Ask which work gets the most feedback and which gets the most enthusiastic feedback. Build on examples already found; ask one focused question at a time and wait when the answer determines the next investigation. Explore who gives that feedback, what they appreciated, and what they subsequently did. Ask about less visible work people rely on even when they rarely acknowledge it.
Use this conversation to develop leads, not to declare a winner. Preserve my interpretation as my account and follow it into the records. Positive feedback may concern convenience, responsiveness, a better decision, a problem avoided, or a material operating result; find out which applies. Read negative feedback and requests for more help too, since they can reveal an important dependency or unmet need.
3. Follow outputs beyond the department
Create a manageable inventory of the team's main work over the selected period, including quiet essential work as well as celebrated outputs. For promising contributions, trace a complete chain:
- What the team did or delivered, when, and for whom.
- The outside team's need, decision, or problem, using its own expressed concerns and records.
- What feedback came back, from whom, and what it specifically referred to.
- How the recipient actually used the work: a decision changed, work enabled, time released, an obstacle removed, or another supported consequence.
- What happened afterward, and how directly the evidence connects it to the team's contribution.
- The team's effort, other contributors, dependencies, contrary cases, and unresolved questions.
Follow reply threads, later meetings, document references, project actions, and operating results. Distinguish praise from use, use from consequence, and a contribution to a result from sole causation. Missing thank-you emails do not establish low value. Look for repeated reliance on uncelebrated work and evidence of what happened when an input was delayed or absent; do not invent the counterfactual benefit of preventing a problem.
For a broad department, divide investigation by outside stakeholder group or complete workstream. Give each agent the shared strategy and purpose, bounded source set, chain above, and instructions to return dated references, gaps, and competing explanations. Maintain coverage of work and recipients. Reconcile overlapping outputs and downstream results yourself so several groups do not each claim the same benefit. If agents are unavailable, perform sequential bounded passes.
4. Compare the contributions with me
Present a short set of the strongest candidates. For each, show what it enables outside the team, the evidence, whose work benefits, its connection to strategy, and approximate effort where known. Label effort estimates and distinguish elapsed time from person-hours. Do not combine unlike benefits into a spurious numerical ranking. Explain why a contribution appears consequential and what could change that judgment.
Include a quiet essential contribution when the evidence supports it. Where enthusiastic feedback and apparent strategic consequence point to different work, make that difference a topic for discussion. Ask me about missing dependencies, unrecorded use, and whether the comparison matches the team's responsibilities. Follow important new leads, revise the account, and leave disputed impact claims explicit. A smaller supported finding is more useful than a confident ranking the records cannot sustain.
5. Develop ways to support more of the valuable work
For the best-supported contributions, propose concrete ways to strengthen or extend them: improve the part recipients actually use, deliver it at a more useful moment, remove an evidenced bottleneck, make an effective practice repeatable, or serve another group with the same demonstrated need. Let the findings determine the proposals.
Explain for each proposal the intended benefit, evidence behind it, effort or dependency, and a small test with an observable result. Ask which changes I want to pursue and wait before recording them as my decisions. Keep any unresolved stakeholder validation visible; a proposed conversation is not feedback you have obtained.
Deliver a concise account of where the department appears to make its largest contribution outside itself, backed by source-linked examples, plus the selected ways to support more of it. Include the scope examined and consequential unknowns. Do not contact colleagues, reallocate work, or announce changes as part of this assessment unless I ask for that execution.
Done when
You have discussed an evidence-based account of the department’s most consequential contributions outside itself and selected any practical ways to strengthen them. The result accounts for enthusiastic feedback, actual use, quiet dependencies, strategy, and effort; unsupported impact claims remain unresolved rather than becoming a ranking.
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.