How well do you stick to strategy?
Look back at the last ten major corporate strategy announcements and ask what happened after the announcement. Which commitments turned into budgets, people and work? Which changed for a reason? Which simply faded? The aim is to understand your firm's habits of follow-through well enough to improve the next strategic commitment.
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 the last ten major strategy announcements and reconstruct what happened to their commitments.
- Trace budgets, staffing, projects, decisions and results, distinguishing implementation, deliberate revision, abandonment and unknown outcomes.
- Compare the histories and develop concrete lessons for the next announcement.
What to have ready
- The company or business scope, plus access to available strategy records and related communications. Specific announcements or exports can fill gaps in the accessible record.
Where you come in
- Confirm which announcements count as major and the period being examined.
- Clarify disputed commitments or undocumented changes, then review the findings and lessons.
What you'll get
You receive a sourced history of ten announcements, or an explicitly smaller set, showing where the firm followed through, changed direction or left the outcome unclear.
You're done when
You can trace the confirmed ten strategy announcements—or the explicitly agreed smaller set—from promises through subsequent action and change, and you have evidence-based proposals for improving the next one.
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 the last ten major announcements Help me understand how well our firm follows through on strategy by examining its last ten major corporate strategy announcements and what happened afterward. Establish the company and scope from the context; ask one focused question if they are unclear. Inspect and try access to connected company documents, contact or role records and associated correspondence, email, company chats and other available messages, leadership calendars and meeting material. Search internal announcements, strategy presentations, leadership transcripts, operating plans and the company website, including dated investor or corporate announcements where relevant. Use company, leader, business-unit and initiative names as search terms. Contact records help identify relevant people and terms; do not contact anyone. Start with the most recent material and search backward far enough to identify ten major announcements. Propose a practical definition of major: a substantive commitment about where the firm will compete, allocate resources or change how it operates. Identify possible repeats of an earlier announcement, local initiatives and statements too vague to classify. Distinguish announcement date from a later file modification date or retrospective reference. Show the proposed set with dates, source links, principal commitments and brief reasons for inclusion. Confirm the definition, scope and set with me before building detailed histories. Combine repeated publicity for the same strategic decision; preserve a subsequent substantive revision as a linked event. If we choose to count a renewed or revised strategy separately, make that choice visible and avoid counting the same implementation twice. If sources are inaccessible, investigate available connection or export options and request specific missing announcements or company documentation. Explain the value of internal access and offer a focused IT request if useful. A website-only history can show public commitments and public results but may leave implementation invisible. If ten cannot be established, agree an achievable set and label the smaller scope throughout. ### 2. Turn each announcement into traceable commitments Extract the intended change, desired result, responsible business or named owner, time horizon and measures of success stated at the time. Separate explicit commitments from your interpretation of the rhetoric. Preserve ambiguous wording and ask about it when the interpretation changes the assessment. Find the baseline and preceding debate in plans, emails, chat threads, leadership meetings and financial or operating records. What problem was this strategy meant to solve? What would doing it have required? Record relevant dependencies and conditions stated in the announcement rather than inventing a success test afterward. Create a coverage record with one entry per announcement, its commitments, source period, linked initiatives and unanswered questions. For a broad investigation, assign complete announcement histories to agents in manageable groups. Give each the same definition, source rules and output format, with an explicit requirement to follow later amendments. Use successive waves or bounded single-session passes if capacity is limited; keep full histories together. ### 3. Follow each commitment into the aftermath Search later budgets, staffing and organization changes, project plans and progress reports, procurement or investment decisions, operating results, internal correspondence and subsequent strategy announcements. Follow initiative renames and the movement of responsibility between teams. Look for what people actually funded and did, not just repeated language. Build a dated chain from announcement to resource decisions, implementation, delivered changes and observed outcomes. Distinguish allocating money from spending it, launching a project from completing it, and achieving an operating change from achieving the intended business result. Use the metrics promised at the time where available; explain when definitions changed or the outcome horizon has not yet arrived. For each commitment, record the most defensible current description: followed through, partly implemented, explicitly revised, abandoned, or outcome unknown. Allow different commitments in one announcement to have different descriptions. Explain the evidence and confidence rather than reducing the announcement to a single unsupported score. A considered strategy change may be good judgment. Find the dated decision, changed conditions and new commitment where the record supports a revision. Silence alone does not prove abandonment. Identify contradictions and ask me one focused question at a time where undocumented decisions materially change the history; mark recollections as such. ### 4. Compare the histories and test the account Reconcile agent findings, repeated commitments and source conflicts. Preserve announcement, event and effective dates. Trace superseding decisions explicitly; a newer mention alone does not establish a reversal. Look for recurring differences between commitments that took hold and those that did not: specificity, ownership, resource alignment, incentives, dependency management, review practice or adaptation to new evidence. Develop these explanations from the histories. Include counterexamples and alternative explanations, such as unusually favorable conditions or a genuinely longer implementation cycle. Do not claim a causal lesson from a correlation alone. Have an independent reviewer inspect the draft histories and relevant source packets for missed amendments, hindsight-based success criteria and overstated implementation or failure. Give the reviewer the evidence and actual draft rather than a defense of the conclusion. If independence is unavailable, use a distinct review pass and disclose that limitation. Repair material findings. ### 5. Deliver the lessons for the next announcement Provide a concise overall finding, a comparison table of the confirmed announcements and their commitments, and readable individual histories with source links, dates, present status and unresolved questions. Make the review date and incomplete coverage clear. Propose a few changes to how the next strategy is announced and followed: each must address a pattern found here and explain what would work differently. For example, if initiatives repeatedly lacked resource decisions, show how the next commitment could state the required allocation and its decision date. Treat these as proposals and invite my corrections. Finish with the strongest supported lesson, the evidence that could change it, and concrete improvements I can choose. Do not contact people, alter company plans or turn recommendations into adopted policy. 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
How well do you stick to strategy?
What the AI will do
- Find the last ten major strategy announcements and reconstruct what happened to their commitments.
- Trace budgets, staffing, projects, decisions and results, distinguishing implementation, deliberate revision, abandonment and unknown outcomes.
- Compare the histories and develop concrete lessons for the next announcement.
What you can provide
- The company or business scope, plus access to available strategy records and related communications. Specific announcements or exports can fill gaps in the accessible record.
Where you'll take part
- Confirm which announcements count as major and the period being examined.
- Clarify disputed commitments or undocumented changes, then review the findings and lessons.
What you'll get
You receive a sourced history of ten announcements, or an explicitly smaller set, showing where the firm followed through, changed direction or left the outcome unclear.
Activity context
Look back at the last ten major corporate strategy announcements and ask what happened after the announcement. Which commitments turned into budgets, people and work? Which changed for a reason? Which simply faded? The aim is to understand your firm's habits of follow-through well enough to improve the next strategic commitment.
For the user
Name the firm or business unit. The AI will look for the strategy announcements and their aftermath before asking you to assemble material. You will confirm the set, help resolve consequential ambiguities and review what the histories suggest about making the next strategy stick.
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 the last ten major announcements
Help me understand how well our firm follows through on strategy by examining its last ten major corporate strategy announcements and what happened afterward. Establish the company and scope from the context; ask one focused question if they are unclear.
Inspect and try access to connected company documents, contact or role records and associated correspondence, email, company chats and other available messages, leadership calendars and meeting material. Search internal announcements, strategy presentations, leadership transcripts, operating plans and the company website, including dated investor or corporate announcements where relevant. Use company, leader, business-unit and initiative names as search terms. Contact records help identify relevant people and terms; do not contact anyone.
Start with the most recent material and search backward far enough to identify ten major announcements. Propose a practical definition of major: a substantive commitment about where the firm will compete, allocate resources or change how it operates. Identify possible repeats of an earlier announcement, local initiatives and statements too vague to classify. Distinguish announcement date from a later file modification date or retrospective reference.
Show the proposed set with dates, source links, principal commitments and brief reasons for inclusion. Confirm the definition, scope and set with me before building detailed histories. Combine repeated publicity for the same strategic decision; preserve a subsequent substantive revision as a linked event. If we choose to count a renewed or revised strategy separately, make that choice visible and avoid counting the same implementation twice.
If sources are inaccessible, investigate available connection or export options and request specific missing announcements or company documentation. Explain the value of internal access and offer a focused IT request if useful. A website-only history can show public commitments and public results but may leave implementation invisible. If ten cannot be established, agree an achievable set and label the smaller scope throughout.
2. Turn each announcement into traceable commitments
Extract the intended change, desired result, responsible business or named owner, time horizon and measures of success stated at the time. Separate explicit commitments from your interpretation of the rhetoric. Preserve ambiguous wording and ask about it when the interpretation changes the assessment.
Find the baseline and preceding debate in plans, emails, chat threads, leadership meetings and financial or operating records. What problem was this strategy meant to solve? What would doing it have required? Record relevant dependencies and conditions stated in the announcement rather than inventing a success test afterward.
Create a coverage record with one entry per announcement, its commitments, source period, linked initiatives and unanswered questions. For a broad investigation, assign complete announcement histories to agents in manageable groups. Give each the same definition, source rules and output format, with an explicit requirement to follow later amendments. Use successive waves or bounded single-session passes if capacity is limited; keep full histories together.
3. Follow each commitment into the aftermath
Search later budgets, staffing and organization changes, project plans and progress reports, procurement or investment decisions, operating results, internal correspondence and subsequent strategy announcements. Follow initiative renames and the movement of responsibility between teams. Look for what people actually funded and did, not just repeated language.
Build a dated chain from announcement to resource decisions, implementation, delivered changes and observed outcomes. Distinguish allocating money from spending it, launching a project from completing it, and achieving an operating change from achieving the intended business result. Use the metrics promised at the time where available; explain when definitions changed or the outcome horizon has not yet arrived.
For each commitment, record the most defensible current description: followed through, partly implemented, explicitly revised, abandoned, or outcome unknown. Allow different commitments in one announcement to have different descriptions. Explain the evidence and confidence rather than reducing the announcement to a single unsupported score.
A considered strategy change may be good judgment. Find the dated decision, changed conditions and new commitment where the record supports a revision. Silence alone does not prove abandonment. Identify contradictions and ask me one focused question at a time where undocumented decisions materially change the history; mark recollections as such.
4. Compare the histories and test the account
Reconcile agent findings, repeated commitments and source conflicts. Preserve announcement, event and effective dates. Trace superseding decisions explicitly; a newer mention alone does not establish a reversal.
Look for recurring differences between commitments that took hold and those that did not: specificity, ownership, resource alignment, incentives, dependency management, review practice or adaptation to new evidence. Develop these explanations from the histories. Include counterexamples and alternative explanations, such as unusually favorable conditions or a genuinely longer implementation cycle. Do not claim a causal lesson from a correlation alone.
Have an independent reviewer inspect the draft histories and relevant source packets for missed amendments, hindsight-based success criteria and overstated implementation or failure. Give the reviewer the evidence and actual draft rather than a defense of the conclusion. If independence is unavailable, use a distinct review pass and disclose that limitation. Repair material findings.
5. Deliver the lessons for the next announcement
Provide a concise overall finding, a comparison table of the confirmed announcements and their commitments, and readable individual histories with source links, dates, present status and unresolved questions. Make the review date and incomplete coverage clear.
Propose a few changes to how the next strategy is announced and followed: each must address a pattern found here and explain what would work differently. For example, if initiatives repeatedly lacked resource decisions, show how the next commitment could state the required allocation and its decision date. Treat these as proposals and invite my corrections.
Finish with the strongest supported lesson, the evidence that could change it, and concrete improvements I can choose. Do not contact people, alter company plans or turn recommendations into adopted policy.
Done when
You can trace the confirmed ten strategy announcements—or the explicitly agreed smaller set—from promises through subsequent action and change, and you have evidence-based proposals for improving the next one.
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.