Steelman the strategy you rejected.
Give the strategy you turned down its strongest fair hearing. You may find a reason to reconsider—or become clearer about why you rejected it.
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
- Reconstruct the rejected strategy and build its strongest evidence-supported case, considering what has changed since the decision.
What to have ready
- The strategy or a description; available messages, meeting records, and decision documents can fill in its history.
Where you come in
- Clarify the original decision and criteria, then judge whether the stronger case warrants reconsideration.
What you'll get
You have a fair, evidence-supported case for the rejected strategy and a comparison with the original reasons, showing what would justify reconsidering it or retaining the decision.
You're done when
You have a fair, evidence-supported case for the rejected strategy and a comparison with the original reasons, showing what would justify reconsidering it or retaining the decision.
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. Steelman the strategy I rejected: build its strongest fair, evidence-supported case and help me examine whether that changes the original decision. ### 1. Reconstruct the actual strategy and its rejection. Read the strategy or account I supplied. Search relevant available emails, messages and chats, meeting transcripts, documents, and project or decision records to establish what was proposed, what it aimed to achieve, its mechanism, and why it was rejected. Identify the alternatives considered and the criteria used at the time. Keep dates clear. Distinguish the original proposal and evidence available then from later commentary or developments. Separate documented reasons, my present recollection, and your interpretation. If the proposal or reasons cannot be reconstructed from the records, interview me with focused questions and build a brief from my answers. Summarize the strategy and the consequential reasons for rejection. Ask me to confirm or correct this account when uncertainty would affect the exercise, and wait before building the case on a disputed premise. Do not substitute a different, easier-to-defend strategy without making the change explicit. ### 2. Build the strongest fair case. A steelman is the strongest reasonable version of an argument, supported by evidence and faithful to its essential idea. Find the strategy’s most compelling purpose, causal logic, advantages, and conditions for success. Explain why an informed advocate might favor it over the alternatives. Investigate the evidence using the supplied records, relevant connected material, and appropriate public primary sources when needed. Look for support the original discussion overlooked and serious counterevidence the strongest case must still face. Do not manufacture certainty, conceal known weaknesses, or assume that defending an idea makes it true. Consider whether circumstances have changed since the rejection. Keep a case that could have been made then separate from one that depends on new information. If modest amendments would materially strengthen the strategy, label them as amendments. When a choice would change the strategic proposition, present the original and revised versions clearly and ask which I want examined before treating the revision as the rejected idea. ### 3. Compare the stronger case with the rejection. - Write a coherent affirmative case, giving its central argument, best evidence, tradeoffs, and necessary assumptions. - Then test it against each consequential original objection. - Identify which objections it answers, which remain, and which depend on a factual gap or a preference I need to judge. Where helpful, present two concrete conclusions with the conditions that would support each: reconsider the strategy if specified evidence holds, or retain the rejection if the remaining objection is decisive. These should follow from the evidence rather than forcing a balanced appearance. Identify what new fact would most change the judgment. ### 4. Discuss and finish. Present the case and comparison, then ask whether they change my view. Wait for my response before representing a decision as mine. If I disagree, explore the substantive reason, check the evidence, and revise the case or comparison where warranted. Deliver a usable written account of the strongest case, its relation to the original reasons, and my judgment if I have supplied one. If I remain undecided, record the open issue and what would help resolve it. An informed decision to keep the rejection is a valid outcome. Do not turn reconsideration into execution of the strategy. 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
Steelman the strategy you rejected.
What the AI will do
- Reconstruct the rejected strategy and build its strongest evidence-supported case, considering what has changed since the decision.
What you can provide
- The strategy or a description; available messages, meeting records, and decision documents can fill in its history.
Where you'll take part
- Clarify the original decision and criteria, then judge whether the stronger case warrants reconsideration.
What you'll get
You have a fair, evidence-supported case for the rejected strategy and a comparison with the original reasons, showing what would justify reconsidering it or retaining the decision.
Activity context
Give the strategy you turned down its strongest fair hearing. You may find a reason to reconsider—or become clearer about why you rejected it.
For the user
Share the rejected strategy, a rough description, or records of the decision. The AI can reconstruct the context from connected documents and discussion. You’ll clarify the original reasons, review the strongest case, and decide whether it changes your judgment.
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
Steelman the strategy I rejected: build its strongest fair, evidence-supported case and help me examine whether that changes the original decision.
1. Reconstruct the actual strategy and its rejection.
Read the strategy or account I supplied. Search relevant available emails, messages and chats, meeting transcripts, documents, and project or decision records to establish what was proposed, what it aimed to achieve, its mechanism, and why it was rejected. Identify the alternatives considered and the criteria used at the time.
Keep dates clear. Distinguish the original proposal and evidence available then from later commentary or developments. Separate documented reasons, my present recollection, and your interpretation. If the proposal or reasons cannot be reconstructed from the records, interview me with focused questions and build a brief from my answers.
Summarize the strategy and the consequential reasons for rejection. Ask me to confirm or correct this account when uncertainty would affect the exercise, and wait before building the case on a disputed premise. Do not substitute a different, easier-to-defend strategy without making the change explicit.
2. Build the strongest fair case.
A steelman is the strongest reasonable version of an argument, supported by evidence and faithful to its essential idea. Find the strategy’s most compelling purpose, causal logic, advantages, and conditions for success. Explain why an informed advocate might favor it over the alternatives.
Investigate the evidence using the supplied records, relevant connected material, and appropriate public primary sources when needed. Look for support the original discussion overlooked and serious counterevidence the strongest case must still face. Do not manufacture certainty, conceal known weaknesses, or assume that defending an idea makes it true.
Consider whether circumstances have changed since the rejection. Keep a case that could have been made then separate from one that depends on new information. If modest amendments would materially strengthen the strategy, label them as amendments. When a choice would change the strategic proposition, present the original and revised versions clearly and ask which I want examined before treating the revision as the rejected idea.
3. Compare the stronger case with the rejection.
- Write a coherent affirmative case, giving its central argument, best evidence, tradeoffs, and necessary assumptions.
- Then test it against each consequential original objection.
- Identify which objections it answers, which remain, and which depend on a factual gap or a preference I need to judge.
Where helpful, present two concrete conclusions with the conditions that would support each: reconsider the strategy if specified evidence holds, or retain the rejection if the remaining objection is decisive. These should follow from the evidence rather than forcing a balanced appearance. Identify what new fact would most change the judgment.
4. Discuss and finish.
Present the case and comparison, then ask whether they change my view. Wait for my response before representing a decision as mine. If I disagree, explore the substantive reason, check the evidence, and revise the case or comparison where warranted.
Deliver a usable written account of the strongest case, its relation to the original reasons, and my judgment if I have supplied one. If I remain undecided, record the open issue and what would help resolve it. An informed decision to keep the rejection is a valid outcome. Do not turn reconsideration into execution of the strategy.
Done when
You have a fair, evidence-supported case for the rejected strategy and a comparison with the original reasons, showing what would justify reconsidering it or retaining the decision.
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.