Find one thing your department can stop doing.
Some work survives because it is on the calendar, in a template, or simply what the department has always done. Have AI investigate which recurring activities may no longer earn their place.
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 recurring work, its effort, and who uses its outputs alongside an interview about your department’s purpose.
- Develop a practical stop, simplify, or automate test for the activity you select, accounting for hidden dependencies.
What to have ready
- Context about your department’s purpose, outputs, and repeated tasks.
- Available examples or permitted access when needed; the AI searches records and does the organizing and estimates.
Where you come in
- Correct the department’s purpose before the AI judges activities, then review the shortlist and choose any work worth pursuing.
- Work through the test’s remaining decisions and review how lost value would be noticed.
What you'll get
An evidence-backed assessment and, for any selected change, a concrete test plan with estimated time released and a review point; a supported decision to change nothing is also possible.
You're done when
You have reviewed the evidence about the recurring activities examined and either selected work worth changing or reached an evidence-backed conclusion that none merits a change. For any selected change, you have a concrete test plan that accounts for hidden dependencies and measures the time released. Unresolved questions about an activity’s value remain explicit; missing evidence alone does not establish that 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. Help me find one or more things my department can stop doing. Investigate the work yourself wherever you have access, and interview me alongside that investigation. Ask one focused question at a time. ### 1. Establish the department's purpose and available evidence. Identify my department from context; ask if unclear. Check and try connections to email, company chat, calendars, and documents created by me or my team. Investigate connection options before asking me to supply missing material. Explain how read-only access would help and offer an IT request if needed. Use an interview and available examples when access cannot be enabled. Interview me to understand the department's core function, how it adds value and serves the firm, its specific outputs, and tasks we perform repeatedly. Build on what I have already supplied. Alongside this interview, examine accessible records; continue independent work while awaiting answers where possible. Summarize the purpose and outputs and resolve misunderstandings before judging which activities may be unnecessary. ### 2. Inventory recurring work and trace its value. Look across a useful recent period in messages, calendars, and documents. Identify repeated meetings, reports, coordination exchanges, approvals, and other work. Follow references to their outputs: who receives them, what decisions or actions use them, and what depends on them? Read responses and later references. These examples are starting points, not an exhaustive list. - For promising candidates, estimate frequency, duration, people involved, and preparation or follow-up effort. - Distinguish elapsed time from person-hours, avoid counting work twice, and label assumptions. - Ask about effort or purpose the records cannot reveal. - Missing visible replies are a reason to investigate use, not proof of no value. ### 3. Propose work worth stopping. Compare the inventory with the department's confirmed purpose. Present an initial shortlist explaining each activity's intended contribution, evidence of actual value, why stopping seems plausible, known dependencies, and potential time and effort released. Cite records where available and distinguish findings from hypotheses. Include work that may belong in a simpler or automated form. Ask for my thoughts and which activities, if any, are worth pursuing. Wait for my selection. ### 4. Work out how to stop the selected activity. For each selection, trace who relies on it and what could break if it disappears. Develop a practical test: people to consult or inform, duration of a pause or reduced version, signs of lost value to monitor, who will notice them, and when to restore or revise the activity. Look for hidden uses such as an input to another team's decision. Explain the implications of stopping altogether. - Where the outcome remains valuable, investigate whether AI can perform the needed work. - Specify inputs, access, actions, output, and human decisions that remain. - Compare this with simply stopping, using the effort and dependencies you established. Deliver a concrete plan for each selected activity: proposed change, people involved, test, estimated time released, and a review point for deciding whether it should stick. Walk me through remaining decisions and revise with me. Do not cancel meetings, notify colleagues, or change recurring work unless I ask you to carry out the plan. 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 one thing your department can stop doing.
What the AI will do
- Investigate recurring work, its effort, and who uses its outputs alongside an interview about your department’s purpose.
- Develop a practical stop, simplify, or automate test for the activity you select, accounting for hidden dependencies.
What you can provide
- Context about your department’s purpose, outputs, and repeated tasks.
- Available examples or permitted access when needed; the AI searches records and does the organizing and estimates.
Where you'll take part
- Correct the department’s purpose before the AI judges activities, then review the shortlist and choose any work worth pursuing.
- Work through the test’s remaining decisions and review how lost value would be noticed.
What you'll get
An evidence-backed assessment and, for any selected change, a concrete test plan with estimated time released and a review point; a supported decision to change nothing is also possible.
Activity context
Some work survives because it is on the calendar, in a template, or simply what the department has always done. Have AI investigate which recurring activities may no longer earn their place.
For the user
Paste the prompt below into your work AI. It will investigate accessible communications, calendars, and documents while asking about your department’s purpose and recurring work.
You’ll discuss its shortlist and choose an activity worth changing. The AI will then develop a practical plan to stop, simplify, or automate it and check whether anything valuable is lost, working through the remaining decisions with you.
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 one or more things my department can stop doing. Investigate the work yourself wherever you have access, and interview me alongside that investigation. Ask one focused question at a time.
1. Establish the department's purpose and available evidence.
Identify my department from context; ask if unclear. Check and try connections to email, company chat, calendars, and documents created by me or my team. Investigate connection options before asking me to supply missing material. Explain how read-only access would help and offer an IT request if needed. Use an interview and available examples when access cannot be enabled.
Interview me to understand the department's core function, how it adds value and serves the firm, its specific outputs, and tasks we perform repeatedly. Build on what I have already supplied. Alongside this interview, examine accessible records; continue independent work while awaiting answers where possible. Summarize the purpose and outputs and resolve misunderstandings before judging which activities may be unnecessary.
2. Inventory recurring work and trace its value.
Look across a useful recent period in messages, calendars, and documents. Identify repeated meetings, reports, coordination exchanges, approvals, and other work. Follow references to their outputs: who receives them, what decisions or actions use them, and what depends on them? Read responses and later references. These examples are starting points, not an exhaustive list.
- For promising candidates, estimate frequency, duration, people involved, and preparation or follow-up effort.
- Distinguish elapsed time from person-hours, avoid counting work twice, and label assumptions.
- Ask about effort or purpose the records cannot reveal.
- Missing visible replies are a reason to investigate use, not proof of no value.
3. Propose work worth stopping.
Compare the inventory with the department's confirmed purpose. Present an initial shortlist explaining each activity's intended contribution, evidence of actual value, why stopping seems plausible, known dependencies, and potential time and effort released. Cite records where available and distinguish findings from hypotheses. Include work that may belong in a simpler or automated form. Ask for my thoughts and which activities, if any, are worth pursuing. Wait for my selection.
4. Work out how to stop the selected activity.
For each selection, trace who relies on it and what could break if it disappears. Develop a practical test: people to consult or inform, duration of a pause or reduced version, signs of lost value to monitor, who will notice them, and when to restore or revise the activity. Look for hidden uses such as an input to another team's decision. Explain the implications of stopping altogether.
- Where the outcome remains valuable, investigate whether AI can perform the needed work.
- Specify inputs, access, actions, output, and human decisions that remain.
- Compare this with simply stopping, using the effort and dependencies you established.
Deliver a concrete plan for each selected activity: proposed change, people involved, test, estimated time released, and a review point for deciding whether it should stick. Walk me through remaining decisions and revise with me. Do not cancel meetings, notify colleagues, or change recurring work unless I ask you to carry out the plan.
Done when
You have reviewed the evidence about the recurring activities examined and either selected work worth changing or reached an evidence-backed conclusion that none merits a change. For any selected change, you have a concrete test plan that accounts for hidden dependencies and measures the time released. Unresolved questions about an activity’s value remain explicit; missing evidence alone does not establish 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.
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.