Map strategy to your team’s capabilities.
A strategy asks people to do particular things well, at particular times. Map those demands against what your team has actually demonstrated—and whether they have time to do 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
- Find the current strategy and turn its priorities into specific work and capability requirements.
- Search team records and work samples for demonstrated expertise and commitments, then build a sourced capability map and use a separate reviewer where available to check it.
What to have ready
- The strategy or initiative and the team in scope, even as rough notes or links.
- Access to relevant rosters, project documents, work samples, emails, chats and meeting records; capacity information is especially useful.
Where you come in
- Confirm consequential interpretations of the strategy and gaps the record cannot settle.
- Choose which staffing, learning, sequencing or AI-support options deserve development.
What you'll get
A capability map that separates demonstrated expertise, available capacity and missing evidence, plus concrete choices for the most consequential gaps.
You're done when
You have a source-linked capability map and concrete responses to consequential gaps, with expertise, availability and unknowns clearly distinguished.
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 map a strategy to my team’s capabilities and develop practical choices for gaps that could prevent execution. Base the map on the work required and evidence of what people have demonstrated, while keeping expertise, capacity and missing evidence separate. ### 1. Find the current strategy and its intended result Start with the strategy, initiative or team I have supplied. Inspect and try relevant connections. Search approved strategy documents, roadmaps, project plans, emails, chats including WhatsApp where accessible, meeting transcripts and calendar-linked planning discussions for intended outcomes, priorities, deadlines, dependencies and decisions about scope. Use the project names and people already identified to focus the inquiry. Establish which version is operative. Link amendments or reversals to the earlier decision; a recent file timestamp alone does not establish authority. Identify the decision this map will inform, such as staffing an initiative, sequencing work or designing development. Find the intended decision makers and their expressed constraints through roles, invitations and actual discussions. Ask one useful question at a time when the scope or interpretation affects what follows, and wait on dependent work. Do not convert an exploratory idea into an adopted strategy. If the record leaves a consequential requirement ambiguous, show the evidence and ask for confirmation before treating it as settled. ### 2. Establish usable evidence about the team Inspect team rosters, role descriptions, project assignments, completed deliverables, work samples, project outcomes, relevant emails, chats and meeting records. Look for specific contributions: who designed an analysis, implemented a system, negotiated an agreement, led a change or repeatedly solved the kind of problem the strategy presents. Use available workload plans and commitments to assess capacity; calendar occupancy alone cannot establish availability. Try access before requesting material. When connections fail, investigate permitted setup, exports or uploads and ask only for the specific missing record. Accept rough examples and my account, labeling them accordingly. If team evidence or capacity data is unavailable, deliver an explicitly provisional map with unanswered questions. Do not turn lack of visible work into a negative assessment of a person. Record source, date, context, contribution and outcome for each useful example. Distinguish demonstrated work from a job title, credential, self-description or someone else’s attribution. Older evidence may establish experience without establishing current proficiency or availability. ### 3. Translate strategy into observable work Break the strategy into consequential work packages and milestones. For each, specify: - The result someone must produce and how success would be recognized. - The capabilities required, stated as concrete actions rather than vague traits. - The level or depth needed and why it matters for this work. - The timing, effort assumption, dependencies and decisions requiring accountable human judgment. Keep the map small enough to guide the decision while preserving crucial specialist requirements. Show where requirements are explicit in the strategy versus inferred by you. Confirm consequential inferred requirements with me before using them to declare a gap. Separate an essential capability from a useful enhancement. ### 4. Match evidence to requirements in bounded investigations For a substantial scope, use agents assigned to bounded strategic requirements or teams. Give each the relevant work packages, precise source set, evidence standards, deliverable fields and completion criterion: every assigned requirement examined, supporting and conflicting examples cited, and unknowns stated. Ask for capability rows, not rankings of people. Keep a coverage record and use successive waves as needed. For each requirement, record evidenced expertise, strength and relevance of the evidence, people or teams with that experience, current commitments, estimated capacity where supported, dependencies and gaps. Label expertise present but unavailable separately from expertise not yet evidenced. A team may collectively cover a requirement without one person possessing every skill. If agents are unavailable, use manageable passes or fresh sessions with source, decision and coverage handoffs. Reconcile overlapping assessments against the actual work samples, avoiding double-counted people or capacity. Identify any shared-context review honestly. ### 5. Develop concrete responses to material gaps Prioritize gaps by their effect on the strategy’s milestones. Investigate the strongest candidates against additional project records before asking me to confirm a consequential unknown. Pause affected staffing conclusions until resolved or an explicitly provisional assumption is agreed. Develop realistic responses: redeploy demonstrated expertise, reduce competing work, change sequencing, pair people, create targeted practice with a reviewed deliverable, seek external expertise, or use AI for a defined part of the work. Explain what each response covers, the remaining human responsibility, effort, timing and evidence needed to judge readiness. Verify actual AI capabilities before relying on them; do not assume a tool substitutes for untested judgment. Ask which responses I want developed when the choice is consequential, then make the chosen options concrete. ### 6. Review and deliver the planning map Give a separate reviewer the actual map, strategy and source evidence without the author’s rationale. Ask it to check requirement fidelity, unsupported judgments about people, expertise-versus-capacity distinctions, outdated evidence and duplicate capacity commitments. Repair material findings. Use a fresh session where needed and disclose any shared-context fallback. Deliver a readable strategy-to-capability matrix, a short account of the most consequential gaps, developed response options and focused questions that would resolve missing evidence. Include source links and an as-of date. State which rows are demonstrated, inferred or unresolved. Finish with planning choices the evidence supports; do not assign people, change roles or present a provisional map as a personnel verdict. 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
Map strategy to your team’s capabilities.
What the AI will do
- Find the current strategy and turn its priorities into specific work and capability requirements.
- Search team records and work samples for demonstrated expertise and commitments, then build a sourced capability map and use a separate reviewer where available to check it.
What you can provide
- The strategy or initiative and the team in scope, even as rough notes or links.
- Access to relevant rosters, project documents, work samples, emails, chats and meeting records; capacity information is especially useful.
Where you'll take part
- Confirm consequential interpretations of the strategy and gaps the record cannot settle.
- Choose which staffing, learning, sequencing or AI-support options deserve development.
What you'll get
A capability map that separates demonstrated expertise, available capacity and missing evidence, plus concrete choices for the most consequential gaps.
Activity context
A strategy asks people to do particular things well, at particular times. Map those demands against what your team has actually demonstrated—and whether they have time to do it.
For the user
Start with the strategy and team you want to examine. The AI will investigate the work and people’s demonstrated contributions before asking you to fill gaps. You will review consequential assumptions and choose which responses to develop. This produces a planning aid; missing evidence about someone is not evidence they lack the skill.
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 map a strategy to my team’s capabilities and develop practical choices for gaps that could prevent execution. Base the map on the work required and evidence of what people have demonstrated, while keeping expertise, capacity and missing evidence separate.
1. Find the current strategy and its intended result
Start with the strategy, initiative or team I have supplied. Inspect and try relevant connections. Search approved strategy documents, roadmaps, project plans, emails, chats including WhatsApp where accessible, meeting transcripts and calendar-linked planning discussions for intended outcomes, priorities, deadlines, dependencies and decisions about scope. Use the project names and people already identified to focus the inquiry.
Establish which version is operative. Link amendments or reversals to the earlier decision; a recent file timestamp alone does not establish authority. Identify the decision this map will inform, such as staffing an initiative, sequencing work or designing development. Find the intended decision makers and their expressed constraints through roles, invitations and actual discussions.
Ask one useful question at a time when the scope or interpretation affects what follows, and wait on dependent work. Do not convert an exploratory idea into an adopted strategy. If the record leaves a consequential requirement ambiguous, show the evidence and ask for confirmation before treating it as settled.
2. Establish usable evidence about the team
Inspect team rosters, role descriptions, project assignments, completed deliverables, work samples, project outcomes, relevant emails, chats and meeting records. Look for specific contributions: who designed an analysis, implemented a system, negotiated an agreement, led a change or repeatedly solved the kind of problem the strategy presents. Use available workload plans and commitments to assess capacity; calendar occupancy alone cannot establish availability.
Try access before requesting material. When connections fail, investigate permitted setup, exports or uploads and ask only for the specific missing record. Accept rough examples and my account, labeling them accordingly. If team evidence or capacity data is unavailable, deliver an explicitly provisional map with unanswered questions. Do not turn lack of visible work into a negative assessment of a person.
Record source, date, context, contribution and outcome for each useful example. Distinguish demonstrated work from a job title, credential, self-description or someone else’s attribution. Older evidence may establish experience without establishing current proficiency or availability.
3. Translate strategy into observable work
Break the strategy into consequential work packages and milestones. For each, specify:
- The result someone must produce and how success would be recognized.
- The capabilities required, stated as concrete actions rather than vague traits.
- The level or depth needed and why it matters for this work.
- The timing, effort assumption, dependencies and decisions requiring accountable human judgment.
Keep the map small enough to guide the decision while preserving crucial specialist requirements. Show where requirements are explicit in the strategy versus inferred by you. Confirm consequential inferred requirements with me before using them to declare a gap. Separate an essential capability from a useful enhancement.
4. Match evidence to requirements in bounded investigations
For a substantial scope, use agents assigned to bounded strategic requirements or teams. Give each the relevant work packages, precise source set, evidence standards, deliverable fields and completion criterion: every assigned requirement examined, supporting and conflicting examples cited, and unknowns stated. Ask for capability rows, not rankings of people. Keep a coverage record and use successive waves as needed.
For each requirement, record evidenced expertise, strength and relevance of the evidence, people or teams with that experience, current commitments, estimated capacity where supported, dependencies and gaps. Label expertise present but unavailable separately from expertise not yet evidenced. A team may collectively cover a requirement without one person possessing every skill.
If agents are unavailable, use manageable passes or fresh sessions with source, decision and coverage handoffs. Reconcile overlapping assessments against the actual work samples, avoiding double-counted people or capacity. Identify any shared-context review honestly.
5. Develop concrete responses to material gaps
Prioritize gaps by their effect on the strategy’s milestones. Investigate the strongest candidates against additional project records before asking me to confirm a consequential unknown. Pause affected staffing conclusions until resolved or an explicitly provisional assumption is agreed.
Develop realistic responses: redeploy demonstrated expertise, reduce competing work, change sequencing, pair people, create targeted practice with a reviewed deliverable, seek external expertise, or use AI for a defined part of the work. Explain what each response covers, the remaining human responsibility, effort, timing and evidence needed to judge readiness. Verify actual AI capabilities before relying on them; do not assume a tool substitutes for untested judgment. Ask which responses I want developed when the choice is consequential, then make the chosen options concrete.
6. Review and deliver the planning map
Give a separate reviewer the actual map, strategy and source evidence without the author’s rationale. Ask it to check requirement fidelity, unsupported judgments about people, expertise-versus-capacity distinctions, outdated evidence and duplicate capacity commitments. Repair material findings. Use a fresh session where needed and disclose any shared-context fallback.
Deliver a readable strategy-to-capability matrix, a short account of the most consequential gaps, developed response options and focused questions that would resolve missing evidence. Include source links and an as-of date. State which rows are demonstrated, inferred or unresolved. Finish with planning choices the evidence supports; do not assign people, change roles or present a provisional map as a personnel verdict.
Done when
You have a source-linked capability map and concrete responses to consequential gaps, with expertise, availability and unknowns clearly distinguished.
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.