Scour email and calendar for hidden patterns.
Your calendar and messages may reveal why important work keeps slipping—and when you do your best work without quite noticing the conditions. Look for patterns with something you can change: fewer back-to-back meetings, more room for creative work, or more of a productive arrangement you rarely repeat.
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
- Compare several complete weeks of calendar history, messages, meeting records, and work outputs to find changeable patterns.
- Show the evidence and possible effect of each promising pattern, then design a small experiment around a change you choose.
What to have ready
- Available calendar, email, chat, and work records; rough exports or examples are welcome if connections are unavailable.
- Your actual energy and creative peaks, important responsibilities, and work the records miss.
Where you come in
- Correct the AI’s interpretation of your weeks and discuss which patterns matter to you.
- Choose a feasible change and decide how to tell whether it helps.
What you'll get
A short, sourced account of the most useful patterns and a practical experiment, with a baseline and a review point, for changing or repeating one of them.
You're done when
You understand the most useful changeable patterns in the weeks examined and have chosen a small experiment with a baseline, intended benefit, and review point—or have made an informed choice to change nothing. Any missing records and uncertain explanations remain explicit.
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. Find hidden patterns in my email and calendar that I can change to make my working life better. Look both for arrangements that get in the way and productive ones I could use more often. Carry this through to a concrete, small experiment I choose. ### 1. Establish the record and what matters Inspect and try access to my calendar history, email, chats including WhatsApp where accessible, meeting notes or transcripts, tasks, and work outputs. Use calendar titles, participants, project names, and message references to find related threads and deliverables. Calendar history shows how time was allocated; exchanges reveal demands and choices; outputs and follow-ups help establish what work actually happened. Investigate relevant connection and export routes before asking me to assemble anything. If necessary, explain what you cannot read and ask for a permitted connection or usable export. Offer to draft an IT request for read-only access when useful. If access cannot be enabled, work from rough calendar exports and selected message or work examples; identify the restricted coverage. Interview recollections may add context, but cannot establish a complete schedule or message history. Begin with several complete recent weeks, normally four to six if accessible and reasonably representative. Identify dates, timezone, workdays, absences, travel, exceptional deadlines, and source gaps. Use supplied role and priority information, supplemented by plans and relevant project exchanges, to understand which work matters. Ask me to correct essential gaps, one question at a time. Ask when I actually tend to have my best energy or creative concentration; do not assume mornings are best for me. ### 2. Reconstruct and compare weeks Build a working account of meetings, commitments, protected work, urgent requests, and visible outputs. Deduplicate overlapping calendar entries and repeated cross-posted messages. Distinguish scheduled time from evidence of attendance, canceled meetings from held ones, and message timestamps from time spent working. Do not add overlapping events into impossible totals or infer achievement from an appointment. Look for repeated arrangements such as: - Back-to-back meetings and the lack of recovery or preparation time. - Fragmented days or blocks repeatedly interrupted by routine demands. - Important work displaced, rescheduled, or left waiting across several weeks. - Creative or demanding work pushed out of the times I say suit it best. - Productive conditions that appear too rarely: preparation before a decision, an uninterrupted block, a particular collaboration, or a useful conversation followed by tangible progress. Follow promising cases into their surrounding exchanges and work products. Who initiated the demand? Was it imposed, negotiated, or chosen? What happened to the work afterward? Compare similar days or weeks where the pattern was absent. Separate a temporary crunch from repetition. Absence of a visible output is a gap to investigate, not proof of an unproductive day. For a large record, divide complete weeks among agents using the same definitions and questions. Require dates, source references, candidate patterns, contrary cases, and unresolved gaps. Keep thread context intact across week boundaries where needed. Reconcile the time slices and remove duplicate events yourself. Without agents, make sequential passes over the same bounded periods. ### 3. Discuss the patterns that have an adjustable part Present a short, prioritized set rather than a catalogue of everything measurable. For each candidate show concrete dated examples, frequency within the period checked, an apparent effect, contrary evidence or uncertainty, and the part that could change. Use counts only where coverage supports them. Do not equate busy calendars with poor performance or sparse calendars with creative work. Talk through the promising findings with me. Ask about off-calendar work, actual attendance, outcomes, energy, obligations, and choices the record cannot explain. Test your interpretation against my experience. A pattern can be real but unavoidable under my responsibilities; look for a useful adjustment inside those constraints. Keep at least one productive arrangement in view if the evidence supports it. Revise the findings with my answers. ### 4. Turn a selected pattern into an experiment Ask which change, if any, I want to try and wait for the choice. Propose a small version that can fit my actual upcoming commitments: for example, protect one suitable work block, space one meeting sequence, or repeat the preparation associated with a better outcome. The specific change must follow the evidence and my priorities. Define the current baseline using the examined weeks, the exact adjustment, when and where to try it, any agreement it needs, what I hope will improve, and an observable comparison. Choose a short trial and review date suited to the pattern. Include an outcome measure as well as the calendar change when feasible—did the important work progress, or did the meeting become easier to prepare for? Name external conditions that could complicate comparison. Keep monitoring light enough that I will actually do it. Deliver a concise pattern brief with source references and the agreed experiment. If I choose no change, record the useful findings and the reason no experiment was selected. Do not rearrange my calendar, contact colleagues, or create an ongoing automation unless I separately request that execution. This activity finishes with an evidence-based choice and a usable experiment design, not a claim that the change has already worked. 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
Scour email and calendar for hidden patterns.
What the AI will do
- Compare several complete weeks of calendar history, messages, meeting records, and work outputs to find changeable patterns.
- Show the evidence and possible effect of each promising pattern, then design a small experiment around a change you choose.
What you can provide
- Available calendar, email, chat, and work records; rough exports or examples are welcome if connections are unavailable.
- Your actual energy and creative peaks, important responsibilities, and work the records miss.
Where you'll take part
- Correct the AI’s interpretation of your weeks and discuss which patterns matter to you.
- Choose a feasible change and decide how to tell whether it helps.
What you'll get
A short, sourced account of the most useful patterns and a practical experiment, with a baseline and a review point, for changing or repeating one of them.
Activity context
Your calendar and messages may reveal why important work keeps slipping—and when you do your best work without quite noticing the conditions. Look for patterns with something you can change: fewer back-to-back meetings, more room for creative work, or more of a productive arrangement you rarely repeat.
For the user
Begin with the prompt below. The AI will investigate your records before asking you to reconstruct your working life. You will explain what scheduled events and message traffic leave out, then choose an adjustment worth trying.
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
Find hidden patterns in my email and calendar that I can change to make my working life better. Look both for arrangements that get in the way and productive ones I could use more often. Carry this through to a concrete, small experiment I choose.
1. Establish the record and what matters
Inspect and try access to my calendar history, email, chats including WhatsApp where accessible, meeting notes or transcripts, tasks, and work outputs. Use calendar titles, participants, project names, and message references to find related threads and deliverables. Calendar history shows how time was allocated; exchanges reveal demands and choices; outputs and follow-ups help establish what work actually happened.
Investigate relevant connection and export routes before asking me to assemble anything. If necessary, explain what you cannot read and ask for a permitted connection or usable export. Offer to draft an IT request for read-only access when useful. If access cannot be enabled, work from rough calendar exports and selected message or work examples; identify the restricted coverage. Interview recollections may add context, but cannot establish a complete schedule or message history.
Begin with several complete recent weeks, normally four to six if accessible and reasonably representative. Identify dates, timezone, workdays, absences, travel, exceptional deadlines, and source gaps. Use supplied role and priority information, supplemented by plans and relevant project exchanges, to understand which work matters. Ask me to correct essential gaps, one question at a time. Ask when I actually tend to have my best energy or creative concentration; do not assume mornings are best for me.
2. Reconstruct and compare weeks
Build a working account of meetings, commitments, protected work, urgent requests, and visible outputs. Deduplicate overlapping calendar entries and repeated cross-posted messages. Distinguish scheduled time from evidence of attendance, canceled meetings from held ones, and message timestamps from time spent working. Do not add overlapping events into impossible totals or infer achievement from an appointment.
Look for repeated arrangements such as:
- Back-to-back meetings and the lack of recovery or preparation time.
- Fragmented days or blocks repeatedly interrupted by routine demands.
- Important work displaced, rescheduled, or left waiting across several weeks.
- Creative or demanding work pushed out of the times I say suit it best.
- Productive conditions that appear too rarely: preparation before a decision, an uninterrupted block, a particular collaboration, or a useful conversation followed by tangible progress.
Follow promising cases into their surrounding exchanges and work products. Who initiated the demand? Was it imposed, negotiated, or chosen? What happened to the work afterward? Compare similar days or weeks where the pattern was absent. Separate a temporary crunch from repetition. Absence of a visible output is a gap to investigate, not proof of an unproductive day.
For a large record, divide complete weeks among agents using the same definitions and questions. Require dates, source references, candidate patterns, contrary cases, and unresolved gaps. Keep thread context intact across week boundaries where needed. Reconcile the time slices and remove duplicate events yourself. Without agents, make sequential passes over the same bounded periods.
3. Discuss the patterns that have an adjustable part
Present a short, prioritized set rather than a catalogue of everything measurable. For each candidate show concrete dated examples, frequency within the period checked, an apparent effect, contrary evidence or uncertainty, and the part that could change. Use counts only where coverage supports them. Do not equate busy calendars with poor performance or sparse calendars with creative work.
Talk through the promising findings with me. Ask about off-calendar work, actual attendance, outcomes, energy, obligations, and choices the record cannot explain. Test your interpretation against my experience. A pattern can be real but unavoidable under my responsibilities; look for a useful adjustment inside those constraints. Keep at least one productive arrangement in view if the evidence supports it. Revise the findings with my answers.
4. Turn a selected pattern into an experiment
Ask which change, if any, I want to try and wait for the choice. Propose a small version that can fit my actual upcoming commitments: for example, protect one suitable work block, space one meeting sequence, or repeat the preparation associated with a better outcome. The specific change must follow the evidence and my priorities.
Define the current baseline using the examined weeks, the exact adjustment, when and where to try it, any agreement it needs, what I hope will improve, and an observable comparison. Choose a short trial and review date suited to the pattern. Include an outcome measure as well as the calendar change when feasible—did the important work progress, or did the meeting become easier to prepare for? Name external conditions that could complicate comparison. Keep monitoring light enough that I will actually do it.
Deliver a concise pattern brief with source references and the agreed experiment. If I choose no change, record the useful findings and the reason no experiment was selected. Do not rearrange my calendar, contact colleagues, or create an ongoing automation unless I separately request that execution. This activity finishes with an evidence-based choice and a usable experiment design, not a claim that the change has already worked.
Done when
You understand the most useful changeable patterns in the weeks examined and have chosen a small experiment with a baseline, intended benefit, and review point—or have made an informed choice to change nothing. Any missing records and uncertain explanations remain explicit.
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.