Run a weekly good, bad, and improvable review.
Let AI reconstruct last week so you can spend the conversation on what to repeat and what to change. A useful review gives successful moments as much attention as frustrating ones, then connects a few adjustments to the week ahead.
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
- Reconstruct the last completed week from calendar events, messages, tasks, meeting records, and visible finished work.
- Discuss what went well and poorly, then connect a few selected adjustments to next week’s real commitments.
What to have ready
- Available work records, or rough calendar and work notes if connections are unavailable.
- What the records missed, how the week felt, and which results mattered to you.
Where you come in
- Correct the account of the week and discuss the good, the bad, and the improvable.
- Choose a few realistic adjustments for next week, including a successful practice worth repeating.
What you'll get
A short weekly review and a few concrete, chosen adjustments tied to the coming week, with a simple way to notice whether they helped.
You're done when
You have a corrected account of last week, a short review of what worked and what did not, and any adjustments you chose for next week. The adjustments fit real upcoming opportunities and include a simple way to notice their effect.
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 review the last completed week: what worked well, what seemed to go poorly, and what I can change next week. Investigate the record, then talk it through with me. Keep the final review brief and practical. ### 1. Reconstruct the week before asking me to retell it Establish the date range and timezone from the current date and my work context; state what you are treating as last week and correct it if I mean a different period. Inspect and try access to calendar events, sent and received email, company chat and other relevant messages, tasks, meeting notes or transcripts, and work I finished or moved forward in that period. Search by the week's projects, meetings, participants, deadlines, and deliverable names. Use earlier context only where needed to understand last week's commitment or result. Calendar events suggest intended activity; messages and task history show changes, requests, and follow-through; completed documents or other outputs help establish what got done. Distinguish due dates, message dates, and actual completion dates. If access is missing, investigate practical connection or export routes first. Explain the specific gap, help me use a permitted route, and offer an IT request if useful. Otherwise welcome a calendar export, rough task list, pasted exchanges, or spoken recollection. Build the best limited account from those and state its basis; do not turn recollection into a verified activity log. Create a compact working account of important commitments, work advanced or finished, interruptions, unresolved items, and promising or frustrating moments. Deduplicate events and repeated messages. Do not infer attendance or achievement from a scheduled appointment. A single investigator should usually be enough for one week; if the record is unusually large, use bounded source passes and reconcile them into one timeline without expanding the time horizon. ### 2. Correct the account with me Show me a brief account of the week, emphasizing consequential work rather than every event. Ask what important work or experience it misses and wait for my response. Include off-calendar thinking, conversations, recovery, or other contributions I report, distinguishing these from the records you inspected. Talk through what worked well, what seemed to go poorly, and what might be improvable. Use specific moments to make the conversation easy. Ask focused follow-ups one at a time where my experience could change your interpretation: which result mattered, what gave me energy, what created friction, or why an obligation crowded out other work. Do not assume I felt good about the busiest or most visibly productive day. For each promising finding, connect the circumstances, what happened, and the apparent effect. Look for something successful to repeat as well as something frustrating to change. Separate one-off events from possible habits; one week can suggest a pattern, but does not establish a permanent trait or long-term trend. Correct explanations when my account or the evidence contradicts them. ### 3. Connect changes to next week's opportunities Inspect the coming week's calendar, known deadlines, project plans, and relevant requests. Identify actual occasions to repeat a useful practice or try a modest adjustment. If those sources are unavailable, ask only for the upcoming commitments necessary to make the change concrete. Present a few possible adjustments, each tied to a finding from last week and a specific situation next week. Include what the change would look like, why it might help, and any dependency on someone else. Prefer actions within my control and consider where my energy and responsibilities make them realistic. Ask which I want to adopt, and wait for my choice. One or two useful changes may be enough; do not manufacture a quota if the week calls for none. ### 4. Write the short review Produce a readable note with three compact parts: what worked, what went poorly or remains uncertain, and the chosen adjustments for next week. Ground the important findings in dated examples or source references. For each chosen adjustment, state the situation or date, the action, the hoped-for effect, and a simple thing to notice afterward. Preserve any unresolved commitments worth keeping in view without turning the review into a new task-management system. Check that the note reflects what I said and what I actually chose. Keep possible habits labeled as hypotheses. Deliver the review and adjustments together; this is a completed weekly review, not a claim that the adjustments have already improved anything. Do not reschedule events, send messages, or create a recurring review automation unless I ask. 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
Run a weekly good, bad, and improvable review.
What the AI will do
- Reconstruct the last completed week from calendar events, messages, tasks, meeting records, and visible finished work.
- Discuss what went well and poorly, then connect a few selected adjustments to next week’s real commitments.
What you can provide
- Available work records, or rough calendar and work notes if connections are unavailable.
- What the records missed, how the week felt, and which results mattered to you.
Where you'll take part
- Correct the account of the week and discuss the good, the bad, and the improvable.
- Choose a few realistic adjustments for next week, including a successful practice worth repeating.
What you'll get
A short weekly review and a few concrete, chosen adjustments tied to the coming week, with a simple way to notice whether they helped.
Activity context
Let AI reconstruct last week so you can spend the conversation on what to repeat and what to change. A useful review gives successful moments as much attention as frustrating ones, then connects a few adjustments to the week ahead.
For the user
Paste the prompt into your work AI. It will first assemble an account of last week from what it can access. You will fill in the gaps and decide what to carry into next week; the result is meant to be short enough to 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 review the last completed week: what worked well, what seemed to go poorly, and what I can change next week. Investigate the record, then talk it through with me. Keep the final review brief and practical.
1. Reconstruct the week before asking me to retell it
Establish the date range and timezone from the current date and my work context; state what you are treating as last week and correct it if I mean a different period. Inspect and try access to calendar events, sent and received email, company chat and other relevant messages, tasks, meeting notes or transcripts, and work I finished or moved forward in that period.
Search by the week's projects, meetings, participants, deadlines, and deliverable names. Use earlier context only where needed to understand last week's commitment or result. Calendar events suggest intended activity; messages and task history show changes, requests, and follow-through; completed documents or other outputs help establish what got done. Distinguish due dates, message dates, and actual completion dates.
If access is missing, investigate practical connection or export routes first. Explain the specific gap, help me use a permitted route, and offer an IT request if useful. Otherwise welcome a calendar export, rough task list, pasted exchanges, or spoken recollection. Build the best limited account from those and state its basis; do not turn recollection into a verified activity log.
Create a compact working account of important commitments, work advanced or finished, interruptions, unresolved items, and promising or frustrating moments. Deduplicate events and repeated messages. Do not infer attendance or achievement from a scheduled appointment. A single investigator should usually be enough for one week; if the record is unusually large, use bounded source passes and reconcile them into one timeline without expanding the time horizon.
2. Correct the account with me
Show me a brief account of the week, emphasizing consequential work rather than every event. Ask what important work or experience it misses and wait for my response. Include off-calendar thinking, conversations, recovery, or other contributions I report, distinguishing these from the records you inspected.
Talk through what worked well, what seemed to go poorly, and what might be improvable. Use specific moments to make the conversation easy. Ask focused follow-ups one at a time where my experience could change your interpretation: which result mattered, what gave me energy, what created friction, or why an obligation crowded out other work. Do not assume I felt good about the busiest or most visibly productive day.
For each promising finding, connect the circumstances, what happened, and the apparent effect. Look for something successful to repeat as well as something frustrating to change. Separate one-off events from possible habits; one week can suggest a pattern, but does not establish a permanent trait or long-term trend. Correct explanations when my account or the evidence contradicts them.
3. Connect changes to next week's opportunities
Inspect the coming week's calendar, known deadlines, project plans, and relevant requests. Identify actual occasions to repeat a useful practice or try a modest adjustment. If those sources are unavailable, ask only for the upcoming commitments necessary to make the change concrete.
Present a few possible adjustments, each tied to a finding from last week and a specific situation next week. Include what the change would look like, why it might help, and any dependency on someone else. Prefer actions within my control and consider where my energy and responsibilities make them realistic. Ask which I want to adopt, and wait for my choice. One or two useful changes may be enough; do not manufacture a quota if the week calls for none.
4. Write the short review
Produce a readable note with three compact parts: what worked, what went poorly or remains uncertain, and the chosen adjustments for next week. Ground the important findings in dated examples or source references. For each chosen adjustment, state the situation or date, the action, the hoped-for effect, and a simple thing to notice afterward. Preserve any unresolved commitments worth keeping in view without turning the review into a new task-management system.
Check that the note reflects what I said and what I actually chose. Keep possible habits labeled as hypotheses. Deliver the review and adjustments together; this is a completed weekly review, not a claim that the adjustments have already improved anything. Do not reschedule events, send messages, or create a recurring review automation unless I ask.
Done when
You have a corrected account of last week, a short review of what worked and what did not, and any adjustments you chose for next week. The adjustments fit real upcoming opportunities and include a simple way to notice their effect.
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.