Turn competitors’ 10-Ks into a strategy critique.
A competitor’s annual filing tells two stories: the strategy management describes and the choices its spending and results reveal. Read them together to sharpen the questions you ask about your own strategy.
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 your strategic questions in plans and market discussions, then retrieve competitors’ actual annual filings.
- Compare stated priorities with spending, segment results and constraints, using bounded research assignments and a separate evidence reviewer where available.
What to have ready
- Competitor names or a market, and the strategic decision you face; rough notes are enough to begin.
- Access to relevant internal plans, emails, chats or meeting records helps connect the findings to your own choices.
Where you come in
- Confirm the competitors, reporting periods and strategic question if the record leaves these unclear.
- Resolve consequential uncertainty about your own strategy and review the implications.
What you'll get
A sourced critique of competitors’ strategies and concrete implications for yours, with comparable figures, alternative explanations and explicit evidence gaps.
You're done when
You have a reviewed, source-linked strategy critique that connects competitors’ disclosed choices and results to your own decision, with comparison limits and unresolved assumptions visible.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Help me turn competitors’ 10-Ks into a strategy critique that improves a real decision about our own business. Investigate the filings and produce the critique, with clear links between strategic claims, resource allocation, results and implications for us. ### 1. Establish the question and comparison Start with the competitors, market or decision I have supplied. Inspect and try relevant connections. Search strategy documents, market reviews, related emails, chats including WhatsApp where accessible, calendar-linked discussions and meeting transcripts for our priorities, assumptions about competitors, planned investments and unresolved choices. Use project and company names to keep searches relevant. Identify the intended readers and decisions from their roles, meeting invitations and expressed questions. Determine the companies and reporting periods that would answer the question. Ask one useful question at a time when these are ambiguous, and wait before dependent research or conclusions. Confirm a consequential comparison or strategic assumption you propose on my behalf; use decisions already provided. Record the agreed question and scope briefly. If internal access fails, investigate connection and permitted upload or export options before requesting specific material. Work from rough notes if necessary, but distinguish my account from documented plans. Without those records, frame our strategy implications as conditional. If primary filings are missing, obtaining them is central to this activity; do not substitute an unsourced company summary. ### 2. Build the filing record Retrieve actual 10-Ks from SEC EDGAR or the company’s investor-relations filing archive, and relevant amendments. Use the latest appropriate filing and earlier periods needed to examine the chosen strategy. For companies using a different annual filing, identify the form and obtain my agreement to the changed comparison when material. Create a source register with company, filing type, fiscal period, filing date, amendment status and direct link. Inspect the business description, management discussion, financial statements and notes, segment disclosures and relevant risks. Use releases or presentations as supplemental management statements, not replacements for the filing. Track fiscal calendars, currencies, accounting changes, segment reorganizations and restatements. Show what was restated and which series you use. A later publication date alone does not supersede an earlier number. Mark comparisons that cannot be made reliably instead of forcing a common denominator. ### 3. Examine strategy in bounded assignments Use separate agents where available for bounded companies or strategic themes. Give each the strategic question, exact filing set and sections, required comparison periods, source references and a completion criterion: every assigned company or theme covered, figures reconciled where possible, and omissions reported. Require a claim-and-evidence table plus a short critique. Track coverage centrally and use waves if capacity is limited. Each investigator should extract: - The strategic claim, management’s proposed mechanism and intended result. - Observable resource commitments: capital expenditure, research and development, acquisitions, operating costs or other disclosed spending relevant to that claim. - Segment growth, profitability, cash generation or operating indicators that bear on results. - Constraints, dependencies and counterevidence, with exact filing references. - What disclosure cannot establish, including allocation that the company does not report. Keep quoted or paraphrased disclosure separate from the investigator’s interpretation. Do not infer a precise initiative budget from an aggregate expense line. If agents are unavailable, use manageable sequential passes or fresh sessions with source, coverage and unresolved-question handoffs; describe any shared-context review honestly. ### 4. Turn observations into a critique Reconcile the completed investigations around the agreed strategic question. Compare what each company says, funds and achieves. Identify apparent alignment, tension, changes of direction and unresolved bets. For each important interpretation, test a credible alternative: investment timing, acquisitions, restructuring, market conditions or reporting changes may explain a pattern. Distinguish an observed association from a causal claim. Look for evidence that could overturn the critique. Do not treat a disclosed risk as proof it has occurred, or a disappointing short-term result as proof the strategy failed. Connect the findings to our choices using the internal record: which assumption deserves revision, which response is worth examining, and what evidence would justify it. Ask about consequential missing context one question at a time; pause the affected recommendation while continuing independent analysis. ### 5. Verify and deliver the decision brief Give an independent reviewer the actual draft, underlying filings and relevant internal source excerpts, without the author’s explanation or intended conclusion. Ask it to check the strongest claims, arithmetic, period comparability, omitted contrary evidence and the support for implications about us. Resolve material findings, preserving remaining disagreements. Use a fresh session when needed; disclose if only a shared-context check is possible. Deliver an executive brief with the main strategic findings, a compact company comparison, evidence-linked critiques, implications for our decision and the questions that remain open. Attach the source register, calculation basis and coverage gaps. State the date and periods covered. Finish with what the evidence permits us to conclude, not a claim to know competitors’ intentions or a decision made on my behalf. 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
Turn competitors’ 10-Ks into a strategy critique.
What the AI will do
- Find your strategic questions in plans and market discussions, then retrieve competitors’ actual annual filings.
- Compare stated priorities with spending, segment results and constraints, using bounded research assignments and a separate evidence reviewer where available.
What you can provide
- Competitor names or a market, and the strategic decision you face; rough notes are enough to begin.
- Access to relevant internal plans, emails, chats or meeting records helps connect the findings to your own choices.
Where you'll take part
- Confirm the competitors, reporting periods and strategic question if the record leaves these unclear.
- Resolve consequential uncertainty about your own strategy and review the implications.
What you'll get
A sourced critique of competitors’ strategies and concrete implications for yours, with comparable figures, alternative explanations and explicit evidence gaps.
Activity context
A competitor’s annual filing tells two stories: the strategy management describes and the choices its spending and results reveal. Read them together to sharpen the questions you ask about your own strategy.
For the user
Begin with a competitor or market and a decision you want to think through. The AI will investigate the internal context and public filings, ask for missing access or a consequential choice when needed, and return a critique you can use in a strategy discussion. If your internal record is unavailable, implications for your company will remain conditional.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Help me turn competitors’ 10-Ks into a strategy critique that improves a real decision about our own business. Investigate the filings and produce the critique, with clear links between strategic claims, resource allocation, results and implications for us.
1. Establish the question and comparison
Start with the competitors, market or decision I have supplied. Inspect and try relevant connections. Search strategy documents, market reviews, related emails, chats including WhatsApp where accessible, calendar-linked discussions and meeting transcripts for our priorities, assumptions about competitors, planned investments and unresolved choices. Use project and company names to keep searches relevant. Identify the intended readers and decisions from their roles, meeting invitations and expressed questions.
Determine the companies and reporting periods that would answer the question. Ask one useful question at a time when these are ambiguous, and wait before dependent research or conclusions. Confirm a consequential comparison or strategic assumption you propose on my behalf; use decisions already provided. Record the agreed question and scope briefly.
If internal access fails, investigate connection and permitted upload or export options before requesting specific material. Work from rough notes if necessary, but distinguish my account from documented plans. Without those records, frame our strategy implications as conditional. If primary filings are missing, obtaining them is central to this activity; do not substitute an unsourced company summary.
2. Build the filing record
Retrieve actual 10-Ks from SEC EDGAR or the company’s investor-relations filing archive, and relevant amendments. Use the latest appropriate filing and earlier periods needed to examine the chosen strategy. For companies using a different annual filing, identify the form and obtain my agreement to the changed comparison when material.
Create a source register with company, filing type, fiscal period, filing date, amendment status and direct link. Inspect the business description, management discussion, financial statements and notes, segment disclosures and relevant risks. Use releases or presentations as supplemental management statements, not replacements for the filing.
Track fiscal calendars, currencies, accounting changes, segment reorganizations and restatements. Show what was restated and which series you use. A later publication date alone does not supersede an earlier number. Mark comparisons that cannot be made reliably instead of forcing a common denominator.
3. Examine strategy in bounded assignments
Use separate agents where available for bounded companies or strategic themes. Give each the strategic question, exact filing set and sections, required comparison periods, source references and a completion criterion: every assigned company or theme covered, figures reconciled where possible, and omissions reported. Require a claim-and-evidence table plus a short critique. Track coverage centrally and use waves if capacity is limited.
Each investigator should extract:
- The strategic claim, management’s proposed mechanism and intended result.
- Observable resource commitments: capital expenditure, research and development, acquisitions, operating costs or other disclosed spending relevant to that claim.
- Segment growth, profitability, cash generation or operating indicators that bear on results.
- Constraints, dependencies and counterevidence, with exact filing references.
- What disclosure cannot establish, including allocation that the company does not report.
Keep quoted or paraphrased disclosure separate from the investigator’s interpretation. Do not infer a precise initiative budget from an aggregate expense line. If agents are unavailable, use manageable sequential passes or fresh sessions with source, coverage and unresolved-question handoffs; describe any shared-context review honestly.
4. Turn observations into a critique
Reconcile the completed investigations around the agreed strategic question. Compare what each company says, funds and achieves. Identify apparent alignment, tension, changes of direction and unresolved bets. For each important interpretation, test a credible alternative: investment timing, acquisitions, restructuring, market conditions or reporting changes may explain a pattern.
Distinguish an observed association from a causal claim. Look for evidence that could overturn the critique. Do not treat a disclosed risk as proof it has occurred, or a disappointing short-term result as proof the strategy failed.
Connect the findings to our choices using the internal record: which assumption deserves revision, which response is worth examining, and what evidence would justify it. Ask about consequential missing context one question at a time; pause the affected recommendation while continuing independent analysis.
5. Verify and deliver the decision brief
Give an independent reviewer the actual draft, underlying filings and relevant internal source excerpts, without the author’s explanation or intended conclusion. Ask it to check the strongest claims, arithmetic, period comparability, omitted contrary evidence and the support for implications about us. Resolve material findings, preserving remaining disagreements. Use a fresh session when needed; disclose if only a shared-context check is possible.
Deliver an executive brief with the main strategic findings, a compact company comparison, evidence-linked critiques, implications for our decision and the questions that remain open. Attach the source register, calculation basis and coverage gaps. State the date and periods covered. Finish with what the evidence permits us to conclude, not a claim to know competitors’ intentions or a decision made on my behalf.
Done when
You have a reviewed, source-linked strategy critique that connects competitors’ disclosed choices and results to your own decision, with comparison limits and unresolved assumptions visible.
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.