Merge the best of 3 plans into one.
Three promising plans can contain one better plan—if their best parts can actually work together.
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
- Investigate the three plans and the records behind their objectives, constraints, objections, and later decisions.
- Compare their strongest parts, resolve incompatible assumptions with you, and write one coherent plan.
What to have ready
- Three plans in any usable form, including rough drafts, slides, notes, or links; whatever you already know about the intended result.
Where you come in
- Choose between consequential tradeoffs the evidence cannot settle and review any proposed changes to scope, resources, or commitments.
What you'll get
You have one integrated plan with a workable sequence, consistent resource assumptions, and a clear explanation of what it keeps, changes, and leaves out.
You're done when
You have one integrated plan with a workable sequence, consistent resource assumptions, and a clear explanation of what it keeps, changes, and leaves out.
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 merge the best of three plans into one plan that can work as a whole. Do not simply alternate sections or preserve one-third of each. Find what serves the objective, then reconcile the assumptions that would otherwise make the combination fall apart. ### 1. Establish the plans and the intended result Accept drafts, slides, notes, pasted text, or links. Locate all three plans and identify their authors, dates, versions, intended audiences, and approval status where available. If fewer than three are supplied, first look for the missing referenced plan through available access; ask for it if needed. Do not invent a third plan or quietly change the activity. Agree a smaller comparison if the missing plan cannot be obtained. Use the material to establish the decision or outcome the combined plan must support, who will use it, and the expected level of detail. If the plans address different objectives or time horizons, explain the mismatch and ask which shared outcome should govern. Wait before evaluating dependent choices. ### 2. Build a common evidence base Search relevant emails, chats and other messages, calendar milestones and planning meetings, meeting records, project documents, budgets, staffing or capacity data, and other relevant company records. Use the plans' names, initiatives, people, dates, and disputed assumptions as search terms. Find the purpose, audience requirements, objections, constraints, prior experiments, and decisions made after each version. Establish decision makers and affected groups from calendar invitations, project roles, correspondence, and recorded discussion. Use their expressed concerns as evaluation criteria; do not treat a simulated stakeholder preference as an actual requirement. Track which later decisions truly supersede earlier ones rather than assuming the newest file wins. Try available connections before asking me to reconstruct the history. If access is missing, investigate practical connection or export routes and offer help obtaining the specific sources. With the three plans alone, compare what they contain and label unverified external assumptions. Explain any limitation that prevents calling the resource model or commitments confirmed. Keep a source and coverage record. For substantial plans, give separate agents one plan each with the same objective, criteria, shared evidence, and a bounded source list. Ask for its mechanism, strongest elements, assumptions, dependencies, omissions, and contradictions, each with references. Have them finish independently before comparison. Split oversized sources or work in waves. Without agents, use separate passes or fresh sessions with explicit handoffs, and describe the actual independence. ### 3. Identify what is worth keeping Compare the plans on a common basis: - Which actions plausibly cause the desired result, and what supports that connection? - Which parts fit known audience needs and constraints? - What resources, capabilities, decisions, and lead times do they require? - Which uncertainties do they test early, and which do they assume away? - What useful detail or mechanism appears in only one plan? Distinguish a well-written section from a well-supported approach. Find overlaps and contradictions before selecting components. Do not merge incompatible estimates, ownership models, definitions of success, or alternative uses of the same budget as though they were additive benefits. ### 4. Resolve the integration choices Draft a compact outline of the proposed combined logic: objective, approach, major stages, and the contribution of each original. Identify choices that materially affect feasibility or intent. For example, an early pilot and a simultaneous enterprise rollout require different sequencing and commitments; explain the practical difference rather than averaging their timelines. Where the evidence supports one route, recommend it with reasons. Where my judgment is needed, ask one focused question at a time, offer concrete alternatives when useful, and wait before writing that choice into the plan. Continue independent drafting. Confirm proposed changes to scope, resources, owners, or deadlines before describing them as my decisions. Already established decisions need not be approved again. ### 5. Write one coherent plan and verify it Write the actual integrated plan for its intended readers. Include the objective and completion criteria, the chosen approach, sequenced actions and deliverables, dependencies, ownership status, timing, resource assumptions, and decision points. Reconcile terminology and remove duplicated work. Explain where the integration adds a necessary bridge absent from the originals. Check the complete sequence, totals where supplied, resource conflicts, and links between assumptions and commitments. Give a fresh reviewer the actual plan, criteria, and necessary evidence without your account of why it is good. Ask whether a team could follow it, where the parts conflict, and what important original strengths were lost. Repair supported findings; use a disclosed separate pass if independent review is unavailable. Deliver the usable combined plan plus a brief keep/change/leave-out account that makes consequential editorial choices traceable. Incorporate my corrections and revise affected sections together. End with explicit unresolved commitments or assumptions. Do not implement the plan or distribute it as part of this activity. 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
Merge the best of 3 plans into one.
What the AI will do
- Investigate the three plans and the records behind their objectives, constraints, objections, and later decisions.
- Compare their strongest parts, resolve incompatible assumptions with you, and write one coherent plan.
What you can provide
- Three plans in any usable form, including rough drafts, slides, notes, or links; whatever you already know about the intended result.
Where you'll take part
- Choose between consequential tradeoffs the evidence cannot settle and review any proposed changes to scope, resources, or commitments.
What you'll get
You have one integrated plan with a workable sequence, consistent resource assumptions, and a clear explanation of what it keeps, changes, and leaves out.
Activity context
Three promising plans can contain one better plan—if their best parts can actually work together.
For the user
Provide the three plans without tidying them first. The AI will investigate what they are trying to achieve, compare them on the same basis, and bring you the choices that genuinely need your judgment before completing the combined plan.
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 merge the best of three plans into one plan that can work as a whole. Do not simply alternate sections or preserve one-third of each. Find what serves the objective, then reconcile the assumptions that would otherwise make the combination fall apart.
1. Establish the plans and the intended result
Accept drafts, slides, notes, pasted text, or links. Locate all three plans and identify their authors, dates, versions, intended audiences, and approval status where available. If fewer than three are supplied, first look for the missing referenced plan through available access; ask for it if needed. Do not invent a third plan or quietly change the activity. Agree a smaller comparison if the missing plan cannot be obtained.
Use the material to establish the decision or outcome the combined plan must support, who will use it, and the expected level of detail. If the plans address different objectives or time horizons, explain the mismatch and ask which shared outcome should govern. Wait before evaluating dependent choices.
2. Build a common evidence base
Search relevant emails, chats and other messages, calendar milestones and planning meetings, meeting records, project documents, budgets, staffing or capacity data, and other relevant company records. Use the plans' names, initiatives, people, dates, and disputed assumptions as search terms. Find the purpose, audience requirements, objections, constraints, prior experiments, and decisions made after each version.
Establish decision makers and affected groups from calendar invitations, project roles, correspondence, and recorded discussion. Use their expressed concerns as evaluation criteria; do not treat a simulated stakeholder preference as an actual requirement. Track which later decisions truly supersede earlier ones rather than assuming the newest file wins.
Try available connections before asking me to reconstruct the history. If access is missing, investigate practical connection or export routes and offer help obtaining the specific sources. With the three plans alone, compare what they contain and label unverified external assumptions. Explain any limitation that prevents calling the resource model or commitments confirmed.
Keep a source and coverage record. For substantial plans, give separate agents one plan each with the same objective, criteria, shared evidence, and a bounded source list. Ask for its mechanism, strongest elements, assumptions, dependencies, omissions, and contradictions, each with references. Have them finish independently before comparison. Split oversized sources or work in waves. Without agents, use separate passes or fresh sessions with explicit handoffs, and describe the actual independence.
3. Identify what is worth keeping
Compare the plans on a common basis:
- Which actions plausibly cause the desired result, and what supports that connection?
- Which parts fit known audience needs and constraints?
- What resources, capabilities, decisions, and lead times do they require?
- Which uncertainties do they test early, and which do they assume away?
- What useful detail or mechanism appears in only one plan?
Distinguish a well-written section from a well-supported approach. Find overlaps and contradictions before selecting components. Do not merge incompatible estimates, ownership models, definitions of success, or alternative uses of the same budget as though they were additive benefits.
4. Resolve the integration choices
Draft a compact outline of the proposed combined logic: objective, approach, major stages, and the contribution of each original. Identify choices that materially affect feasibility or intent. For example, an early pilot and a simultaneous enterprise rollout require different sequencing and commitments; explain the practical difference rather than averaging their timelines.
Where the evidence supports one route, recommend it with reasons. Where my judgment is needed, ask one focused question at a time, offer concrete alternatives when useful, and wait before writing that choice into the plan. Continue independent drafting. Confirm proposed changes to scope, resources, owners, or deadlines before describing them as my decisions. Already established decisions need not be approved again.
5. Write one coherent plan and verify it
Write the actual integrated plan for its intended readers. Include the objective and completion criteria, the chosen approach, sequenced actions and deliverables, dependencies, ownership status, timing, resource assumptions, and decision points. Reconcile terminology and remove duplicated work. Explain where the integration adds a necessary bridge absent from the originals.
Check the complete sequence, totals where supplied, resource conflicts, and links between assumptions and commitments. Give a fresh reviewer the actual plan, criteria, and necessary evidence without your account of why it is good. Ask whether a team could follow it, where the parts conflict, and what important original strengths were lost. Repair supported findings; use a disclosed separate pass if independent review is unavailable.
Deliver the usable combined plan plus a brief keep/change/leave-out account that makes consequential editorial choices traceable. Incorporate my corrections and revise affected sections together. End with explicit unresolved commitments or assumptions. Do not implement the plan or distribute it as part of this activity.
Done when
You have one integrated plan with a workable sequence, consistent resource assumptions, and a clear explanation of what it keeps, changes, and leaves out.
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.