Find and fix your proposal’s weakest point.
Find the objection that could sink your proposal, then strengthen the proposal where it matters most.
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
- Identify the proposal’s most consequential weakness using its audience, decision context, and supporting evidence.
- Repair the argument or supporting work and produce a revised proposal.
What to have ready
- The proposal, notes, or an accessible link; connected feedback and project records can supply context.
Where you come in
- Clarify the desired decision and choose between repairs that would change the proposal’s commitments or direction.
What you'll get
You have a revised proposal addressing its most consequential supported weakness, with the repair checked and any remaining evidence or decision gap made explicit.
You're done when
You have a revised proposal addressing its most consequential supported weakness, with the repair checked and any remaining evidence or decision gap made 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. Find and fix the weakest point in my proposal—the weakness most likely to undermine the decision I want it to support. ### 1. Understand the proposal and decision context. Read the complete proposal and supporting material, including figures, appendices, and linked sources you can access. Identify the requested decision, intended audience, proposed benefit, mechanism, resources, and commitments. Help me share missing material in a supported form where needed. Search relevant available emails, messages and chats, meeting transcripts, stakeholder feedback, documents, and project files. Look for the audience’s stated criteria, prior objections, unanswered questions, and decisions that change the context. Distinguish documented concerns from your inference about how a reader might respond. Check chronology so old objections already resolved are not presented as current. Ask focused questions where my purpose or the decision-maker’s requirements remain unclear. If the proposal could serve two different decisions, describe them concretely and wait for clarification before choosing the standard against which to assess it. ### 2. Identify the consequential weakness. Trace how the proposal’s actions are supposed to produce its benefits and why this audience should accept the case. Examine the evidence, assumptions, economics or resource implications where relevant, feasibility, alternatives, and the clarity of the decision request. Look for a missing causal link or unaddressed objection, not merely an awkward sentence. Consider several candidate weaknesses before selecting the one whose repair would matter most. Explain the mechanism: what does the proposal depend on, where is the support weak, and how would that affect the intended decision? Cite specific passages and relevant contextual evidence. Distinguish a demonstrated problem from an important uncertainty. If no major weakness is supported, say so and identify the most useful narrower improvement without inventing a fatal flaw. ### 3. Develop and make the repair. Investigate the missing support using available internal sources and suitable public primary evidence where needed. Do the analysis, comparison, calculation, or rewriting required. If the problem is a choice about goals, resources, or commitments, offer two concrete repair approaches when helpful, explain their implications, and ask me to choose. Wait before representing a new commitment as mine. Revise the actual proposal, including surrounding passages that need to change for consistency. Preserve its strongest material and intended purpose. Do not disguise an evidence gap with more confident language. Where missing information prevents a complete repair, improve what can be improved and state the exact evidence or decision still needed. ### 4. Test the revised case and deliver. - Read the revised proposal as the intended decision-maker, testing whether the identified objection is answered and whether the repair introduces a new contradiction, unsupported claim, or commitment. - Check calculations and source references where relevant. - Use a fresh reviewer with the revised proposal and decision criteria if available and useful; resolve material findings rather than merely appending a critique. Deliver the revised proposal in an editable form, with a concise explanation of the original weakness, the change, and any remaining gap. Invite my corrections and incorporate them. The result is a stronger proposal; do not imply that it has won approval or that its predicted benefits have occurred. 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
Find and fix your proposal’s weakest point.
What the AI will do
- Identify the proposal’s most consequential weakness using its audience, decision context, and supporting evidence.
- Repair the argument or supporting work and produce a revised proposal.
What you can provide
- The proposal, notes, or an accessible link; connected feedback and project records can supply context.
Where you'll take part
- Clarify the desired decision and choose between repairs that would change the proposal’s commitments or direction.
What you'll get
You have a revised proposal addressing its most consequential supported weakness, with the repair checked and any remaining evidence or decision gap made explicit.
Activity context
Find the objection that could sink your proposal, then strengthen the proposal where it matters most.
For the user
Share the proposal in any usable form. The AI can investigate the surrounding correspondence, stakeholder feedback, and project evidence. You’ll clarify the intended decision, settle any substantive choice, and review the revised proposal.
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
Find and fix the weakest point in my proposal—the weakness most likely to undermine the decision I want it to support.
1. Understand the proposal and decision context.
Read the complete proposal and supporting material, including figures, appendices, and linked sources you can access. Identify the requested decision, intended audience, proposed benefit, mechanism, resources, and commitments. Help me share missing material in a supported form where needed.
Search relevant available emails, messages and chats, meeting transcripts, stakeholder feedback, documents, and project files. Look for the audience’s stated criteria, prior objections, unanswered questions, and decisions that change the context. Distinguish documented concerns from your inference about how a reader might respond. Check chronology so old objections already resolved are not presented as current.
Ask focused questions where my purpose or the decision-maker’s requirements remain unclear. If the proposal could serve two different decisions, describe them concretely and wait for clarification before choosing the standard against which to assess it.
2. Identify the consequential weakness.
Trace how the proposal’s actions are supposed to produce its benefits and why this audience should accept the case. Examine the evidence, assumptions, economics or resource implications where relevant, feasibility, alternatives, and the clarity of the decision request. Look for a missing causal link or unaddressed objection, not merely an awkward sentence.
Consider several candidate weaknesses before selecting the one whose repair would matter most. Explain the mechanism: what does the proposal depend on, where is the support weak, and how would that affect the intended decision? Cite specific passages and relevant contextual evidence. Distinguish a demonstrated problem from an important uncertainty. If no major weakness is supported, say so and identify the most useful narrower improvement without inventing a fatal flaw.
3. Develop and make the repair.
Investigate the missing support using available internal sources and suitable public primary evidence where needed. Do the analysis, comparison, calculation, or rewriting required. If the problem is a choice about goals, resources, or commitments, offer two concrete repair approaches when helpful, explain their implications, and ask me to choose. Wait before representing a new commitment as mine.
Revise the actual proposal, including surrounding passages that need to change for consistency. Preserve its strongest material and intended purpose. Do not disguise an evidence gap with more confident language. Where missing information prevents a complete repair, improve what can be improved and state the exact evidence or decision still needed.
4. Test the revised case and deliver.
- Read the revised proposal as the intended decision-maker, testing whether the identified objection is answered and whether the repair introduces a new contradiction, unsupported claim, or commitment.
- Check calculations and source references where relevant.
- Use a fresh reviewer with the revised proposal and decision criteria if available and useful; resolve material findings rather than merely appending a critique.
Deliver the revised proposal in an editable form, with a concise explanation of the original weakness, the change, and any remaining gap. Invite my corrections and incorporate them. The result is a stronger proposal; do not imply that it has won approval or that its predicted benefits have occurred.
Done when
You have a revised proposal addressing its most consequential supported weakness, with the repair checked and any remaining evidence or decision gap made 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.