Make recurring reports write themselves.
Point AI toward a routine report and its past editions. It will trace the inputs, draft the next edition, and work out how to have future drafts ready when you need them.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Find past editions, trace how the report is made, and gather the latest inputs.
- Draft the next edition when you agree, then help create an accepted recurring setup or a reusable way to request future drafts.
What to have ready
- The report’s name or identifying context, plus any editions you already have as files, links, or pasted text.
- Missing examples or access only when needed; the AI looks for at least two editions and helps with permitted export options.
Where you come in
- Agree to a current draft, review it, and approve the revision before recurring setup begins.
- Decide whether to create future drafts and confirm their cadence, day, time, time zone, and delivery destination.
What you'll get
An approved current draft and either a verified schedule with delivery to you or reusable on-demand instructions with calendar reminder details.
You're done when
You have an approved current draft and either a verified schedule with delivery to you, or a reusable way to generate the next report on demand with clear reminder instructions.
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. ### 1. Find past editions of the report Help me make this recurring report draft itself. Start with the report context and editions I have already supplied. Inspect your available connections and try to locate at least two identifiable past editions in accessible files, email, chats, or corporate sources before asking me to provide them. If you cannot tell which report I mean, ask for the smallest identifying detail needed to search. If fewer than two editions are accessible, investigate permitted setup or export options, then ask for the missing examples as files, links, or pasted text, and offer help making them available. Use what is available to begin the investigation and explain any limits on establishing the recurring pattern. Ask focused questions one at a time and do the investigation yourself. ### 2. Trace the report and gather current inputs - Read the reports to identify their purpose, audience, structure, cadence, and the sources feeding each section. - Trace how inputs were obtained or calculated through source links, formulas, attachments, and related accessible material. - Reconstruct calculations where the evidence permits and check them against the past editions. - Inspect your available connections and try to find the latest inputs in relevant corporate data sources, my email and chats, and other accessible sources. - Trace figures and claims to their sources and dates. - Identify missing or stale inputs instead of inventing replacements. - After investigating, ask about consequential unresolved inputs, calculations, or context that affect the report. - Build on answers already supplied; explain nonblocking uncertainty and continue useful work. If a necessary connection is absent, investigate what is possible in my setup, then ask for the specific connection or permission needed. If access appears unavailable, explain what corporate approval might enable it, such as permission to use computer control or to build an MCP connection, a way for an AI to query a particular data source. Verify that an approach is allowed before recommending it. Explain any remaining gap and how it affects the report. ### 3. Draft, revise, and obtain approval Offer to draft the report from the latest information. When I agree, produce it in the established format, with unresolved inputs clearly marked, and ask for my review. Wait for my response, revise it from my feedback, and obtain my approval of the revised draft before moving to the recurring setup. ### 4. Agree on the recurring setup After I approve the draft, offer to prepare future drafts on the report's cadence. Infer the cadence from the examples where possible; confirm the required day, time, time zone, and delivery destination. Inspect the tools and permissions available before choosing whether to save this as a prompt, skill, tool, or script. Choose the simplest permitted approach and create it when I accept. ### 5. Set up supported scheduling and delivery If scheduling is available, set up the recurring task after I agree. Check that a future run can access both the instructions and the required sources. Arrange delivery to me through a supported destination, such as email or the app's notifications, and verify the setup with the available tools. Tell me exactly what was created and how the draft will reach me. ### 6. Provide an on-demand fallback when needed If scheduling or delivery is unavailable, explain the specific limit. Give me ready-to-copy calendar reminder details and the simplest reusable instruction or invocation for generating the report on demand. Do not describe an on-demand setup as automated. 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
Make recurring reports write themselves.
What the AI will do
- Find past editions, trace how the report is made, and gather the latest inputs.
- Draft the next edition when you agree, then help create an accepted recurring setup or a reusable way to request future drafts.
What you can provide
- The report’s name or identifying context, plus any editions you already have as files, links, or pasted text.
- Missing examples or access only when needed; the AI looks for at least two editions and helps with permitted export options.
Where you'll take part
- Agree to a current draft, review it, and approve the revision before recurring setup begins.
- Decide whether to create future drafts and confirm their cadence, day, time, time zone, and delivery destination.
What you'll get
An approved current draft and either a verified schedule with delivery to you or reusable on-demand instructions with calendar reminder details.
Activity context
Point AI toward a routine report and its past editions. It will trace the inputs, draft the next edition, and work out how to have future drafts ready when you need them.
For the user
Name the report or share whatever examples you have as files, links, or pasted text, then use this prompt. The AI will look for past editions and trace the sources before asking you to fill consequential gaps. You will agree to a current draft and review it; once it is right, you will decide whether to set up future drafts and confirm when and where they should arrive. Where scheduling is unavailable, it will give you a reusable way to request each edition with reminder instructions.
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
1. Find past editions of the report
Help me make this recurring report draft itself. Start with the report context and editions I have already supplied. Inspect your available connections and try to locate at least two identifiable past editions in accessible files, email, chats, or corporate sources before asking me to provide them. If you cannot tell which report I mean, ask for the smallest identifying detail needed to search.
If fewer than two editions are accessible, investigate permitted setup or export options, then ask for the missing examples as files, links, or pasted text, and offer help making them available. Use what is available to begin the investigation and explain any limits on establishing the recurring pattern. Ask focused questions one at a time and do the investigation yourself.
2. Trace the report and gather current inputs
-
Read the reports to identify their purpose, audience, structure, cadence, and the sources feeding each section.
-
Trace how inputs were obtained or calculated through source links, formulas, attachments, and related accessible material.
-
Reconstruct calculations where the evidence permits and check them against the past editions.
-
Inspect your available connections and try to find the latest inputs in relevant corporate data sources, my email and chats, and other accessible sources.
-
Trace figures and claims to their sources and dates.
-
Identify missing or stale inputs instead of inventing replacements.
-
After investigating, ask about consequential unresolved inputs, calculations, or context that affect the report.
-
Build on answers already supplied; explain nonblocking uncertainty and continue useful work.
If a necessary connection is absent, investigate what is possible in my setup, then ask for the specific connection or permission needed. If access appears unavailable, explain what corporate approval might enable it, such as permission to use computer control or to build an MCP connection, a way for an AI to query a particular data source. Verify that an approach is allowed before recommending it.
Explain any remaining gap and how it affects the report.
3. Draft, revise, and obtain approval
Offer to draft the report from the latest information. When I agree, produce it in the established format, with unresolved inputs clearly marked, and ask for my review. Wait for my response, revise it from my feedback, and obtain my approval of the revised draft before moving to the recurring setup.
4. Agree on the recurring setup
After I approve the draft, offer to prepare future drafts on the report's cadence. Infer the cadence from the examples where possible; confirm the required day, time, time zone, and delivery destination. Inspect the tools and permissions available before choosing whether to save this as a prompt, skill, tool, or script. Choose the simplest permitted approach and create it when I accept.
5. Set up supported scheduling and delivery
If scheduling is available, set up the recurring task after I agree. Check that a future run can access both the instructions and the required sources. Arrange delivery to me through a supported destination, such as email or the app's notifications, and verify the setup with the available tools. Tell me exactly what was created and how the draft will reach me.
6. Provide an on-demand fallback when needed
If scheduling or delivery is unavailable, explain the specific limit. Give me ready-to-copy calendar reminder details and the simplest reusable instruction or invocation for generating the report on demand. Do not describe an on-demand setup as automated.
Done when
You have an approved current draft and either a verified schedule with delivery to you, or a reusable way to generate the next report on demand with clear reminder instructions.
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.