Give every stakeholder a personalized report.
Different people need different things from the same project update. Make each report useful to the decision its reader actually faces.
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
- Establish one verified account of the project, then tailor a real report to each stakeholder’s decisions and documented needs.
- Check that the versions change emphasis and detail while keeping facts, dates and uncertainties consistent.
What to have ready
- A project, reporting occasion or source report, plus any known recipients.
- Access to project data, roles, correspondence, meeting records and earlier feedback helps the AI identify who needs what.
Where you come in
- Resolve unclear audiences, factual conflicts or consequential differences in what recipients should receive.
- Review the completed reports and any proposed decisions or commitments stated in your name.
What you'll get
A checked set of stakeholder reports with consistent facts, useful recipient-specific emphasis and source references; limited-source reports clearly identify their gaps.
You're done when
You have a usable report for each agreed stakeholder, tailored to their documented needs and checked against a common factual account, with unresolved evidence and any missing reports 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. Create personalized reports for the stakeholders in a project or reporting occasion. Establish the evidence once, learn what each reader needs, and write the actual reports. Ask focused questions one at a time and pause where an unresolved choice materially affects the result. ### 1. Establish the reporting occasion and recipients Start with the project, source report, deadline or recipient information I supplied. Inspect available document, project-data, email, calendar, transcript and chat tools with small relevant reads. Search the project brief, team roles, meeting invitations and relevant correspondence to identify stakeholders and the reporting purpose. Include relevant WhatsApp or other messages where accessible. For each possible recipient, look for their requests, earlier feedback, decisions, responsibilities and unanswered questions. Use their actual correspondence and meeting exchanges to understand vocabulary, preferred level of detail and what they need to act on. Do not assume that every finance leader wants the same report or every executive wants only a summary. Build a short recipient record with identity, role, decision or use, timing, documented needs and source links. Resolve consequential ambiguity about who should receive a report or the occasion it serves before drafting that version. Use existing decisions where clear. Investigate available access and export routes before asking me to gather missing material; if records remain unavailable, use my account with its provenance explicit. ### 2. Build the common factual account Retrieve the underlying project documents, data, milestone updates, meeting decisions and relevant emails or chats. Establish the reporting period and an explicit as-of date. Inspect definitions, units, denominators and reporting periods behind key metrics; do not copy a persuasive number without knowing what it measures. Create a source-linked working account covering: - Objective, scope and current status. - Results and progress against the relevant baseline or commitment. - Material problems, dependencies and unresolved questions. - Decisions already made, current choices and actual commitments. - Next milestones, owners and dates when established. Trace conflicting statements to their sources. Check later approval messages, meeting decisions and changed project records for evidence of supersession; recency alone does not confer authority. If a consequential conflict cannot be resolved from evidence, explain it and ask me before treating one version as definitive. Continue uncontested sections while waiting. Separate source facts, analysis, estimates and proposed recommendations in the common account. Give important claims stable references so every tailored report can be traced back to the same evidence. Mark unavailable data and its effect; do not fill the report with invented precision. For a substantial project, divide evidence work into bounded topics or reporting periods. Give each agent actual source material, extraction questions and completion criteria, and track coverage. Reconcile findings centrally before using the account as the basis for personalization. Use waves, manageable sequential passes or explicit fresh-session handoffs as capability requires. ### 3. Decide how each report should differ Map the common facts to each recipient's evidenced decisions and concerns. Specify a practical format, appropriate length, emphasis and any needed supporting detail. For example, a sponsor deciding whether to extend a pilot needs the decision, evidence and tradeoff; an operating owner planning next month's work needs dependencies, dates and responsibilities. Use these as illustrations, not assumed profiles of my actual recipients. Where two formats would serve materially different purposes, explain the practical difference with a small outline and recommend one. Ask only when the choice remains consequential and unresolved, then wait before the affected drafting. Identify any information whose audience or sharing scope is unclear and settle that specific question; do not invent restrictions or distribute reports automatically. ### 4. Write the actual personalized reports Use separate drafting agents for materially different audiences when useful. Give each the verified factual account with sources, the recipient's evidence-based needs, the reporting purpose, agreed format and unresolved limits. Require an actual finished report, with a clear main point, the evidence that reader needs, relevant implications and a concrete decision or next step where supported. Do not let separate writers research themselves into contradictory versions of the project. Return proposed factual additions to the lead for source verification and common-account reconciliation before incorporating them. Tailor order, detail, vocabulary and examples while preserving numbers, dates, commitments and the significance of uncertainty. A problem cannot disappear from one version simply because it is inconvenient for that audience. If multiple agents are unavailable, draft recipient versions in bounded passes with explicit handoffs. Keep a recipient coverage list so no agreed report is silently omitted. Where a proposed recommendation or commitment would be presented as my decision, obtain my confirmation before finalizing it as mine. ### 5. Check across reports and deliver Give an independent reviewer the actual reports, common factual account, source evidence and recipient records without the writers' intentions or rationale. Ask it to check factual consistency, missing consequential context, audience fit and whether each requested decision is supported. For a large set, review in waves and perform a final cross-report check of shared metrics, dates and commitments. Use fresh-session review if available; otherwise disclose same-context review limits. Repair substantive findings and reread the revised reports. Deliver each report in its agreed usable format, labeled for its recipient, with source references and a concise account of unresolved evidence. Include a short comparison of how the versions differ when it helps me review them. Invite corrections and revise affected versions consistently. Stop with the completed reports; sending or publishing them requires my authorization. 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
Give every stakeholder a personalized report.
What the AI will do
- Establish one verified account of the project, then tailor a real report to each stakeholder’s decisions and documented needs.
- Check that the versions change emphasis and detail while keeping facts, dates and uncertainties consistent.
What you can provide
- A project, reporting occasion or source report, plus any known recipients.
- Access to project data, roles, correspondence, meeting records and earlier feedback helps the AI identify who needs what.
Where you'll take part
- Resolve unclear audiences, factual conflicts or consequential differences in what recipients should receive.
- Review the completed reports and any proposed decisions or commitments stated in your name.
What you'll get
A checked set of stakeholder reports with consistent facts, useful recipient-specific emphasis and source references; limited-source reports clearly identify their gaps.
Activity context
Different people need different things from the same project update. Make each report useful to the decision its reader actually faces.
For the user
Name the project or share the report you are starting from. The AI will investigate the underlying facts and the stakeholders’ needs, then write the reports. You may need to clarify an audience, settle a contradiction or review a consequential recommendation.
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
Create personalized reports for the stakeholders in a project or reporting occasion. Establish the evidence once, learn what each reader needs, and write the actual reports. Ask focused questions one at a time and pause where an unresolved choice materially affects the result.
1. Establish the reporting occasion and recipients
Start with the project, source report, deadline or recipient information I supplied. Inspect available document, project-data, email, calendar, transcript and chat tools with small relevant reads. Search the project brief, team roles, meeting invitations and relevant correspondence to identify stakeholders and the reporting purpose. Include relevant WhatsApp or other messages where accessible.
For each possible recipient, look for their requests, earlier feedback, decisions, responsibilities and unanswered questions. Use their actual correspondence and meeting exchanges to understand vocabulary, preferred level of detail and what they need to act on. Do not assume that every finance leader wants the same report or every executive wants only a summary.
Build a short recipient record with identity, role, decision or use, timing, documented needs and source links. Resolve consequential ambiguity about who should receive a report or the occasion it serves before drafting that version. Use existing decisions where clear. Investigate available access and export routes before asking me to gather missing material; if records remain unavailable, use my account with its provenance explicit.
2. Build the common factual account
Retrieve the underlying project documents, data, milestone updates, meeting decisions and relevant emails or chats. Establish the reporting period and an explicit as-of date. Inspect definitions, units, denominators and reporting periods behind key metrics; do not copy a persuasive number without knowing what it measures.
Create a source-linked working account covering:
- Objective, scope and current status.
- Results and progress against the relevant baseline or commitment.
- Material problems, dependencies and unresolved questions.
- Decisions already made, current choices and actual commitments.
- Next milestones, owners and dates when established.
Trace conflicting statements to their sources. Check later approval messages, meeting decisions and changed project records for evidence of supersession; recency alone does not confer authority. If a consequential conflict cannot be resolved from evidence, explain it and ask me before treating one version as definitive. Continue uncontested sections while waiting.
Separate source facts, analysis, estimates and proposed recommendations in the common account. Give important claims stable references so every tailored report can be traced back to the same evidence. Mark unavailable data and its effect; do not fill the report with invented precision.
For a substantial project, divide evidence work into bounded topics or reporting periods. Give each agent actual source material, extraction questions and completion criteria, and track coverage. Reconcile findings centrally before using the account as the basis for personalization. Use waves, manageable sequential passes or explicit fresh-session handoffs as capability requires.
3. Decide how each report should differ
Map the common facts to each recipient's evidenced decisions and concerns. Specify a practical format, appropriate length, emphasis and any needed supporting detail. For example, a sponsor deciding whether to extend a pilot needs the decision, evidence and tradeoff; an operating owner planning next month's work needs dependencies, dates and responsibilities. Use these as illustrations, not assumed profiles of my actual recipients.
Where two formats would serve materially different purposes, explain the practical difference with a small outline and recommend one. Ask only when the choice remains consequential and unresolved, then wait before the affected drafting. Identify any information whose audience or sharing scope is unclear and settle that specific question; do not invent restrictions or distribute reports automatically.
4. Write the actual personalized reports
Use separate drafting agents for materially different audiences when useful. Give each the verified factual account with sources, the recipient's evidence-based needs, the reporting purpose, agreed format and unresolved limits. Require an actual finished report, with a clear main point, the evidence that reader needs, relevant implications and a concrete decision or next step where supported.
Do not let separate writers research themselves into contradictory versions of the project. Return proposed factual additions to the lead for source verification and common-account reconciliation before incorporating them. Tailor order, detail, vocabulary and examples while preserving numbers, dates, commitments and the significance of uncertainty. A problem cannot disappear from one version simply because it is inconvenient for that audience.
If multiple agents are unavailable, draft recipient versions in bounded passes with explicit handoffs. Keep a recipient coverage list so no agreed report is silently omitted. Where a proposed recommendation or commitment would be presented as my decision, obtain my confirmation before finalizing it as mine.
5. Check across reports and deliver
Give an independent reviewer the actual reports, common factual account, source evidence and recipient records without the writers' intentions or rationale. Ask it to check factual consistency, missing consequential context, audience fit and whether each requested decision is supported. For a large set, review in waves and perform a final cross-report check of shared metrics, dates and commitments. Use fresh-session review if available; otherwise disclose same-context review limits.
Repair substantive findings and reread the revised reports. Deliver each report in its agreed usable format, labeled for its recipient, with source references and a concise account of unresolved evidence. Include a short comparison of how the versions differ when it helps me review them. Invite corrections and revise affected versions consistently. Stop with the completed reports; sending or publishing them requires my authorization.
Done when
You have a usable report for each agreed stakeholder, tailored to their documented needs and checked against a common factual account, with unresolved evidence and any missing reports 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.