Find a sprawling project’s one next move.
When a project has sprawled into dozens of threads, the most useful answer can be one action that makes the rest easier.
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 project’s current objective, progress, dependencies, and unresolved decisions from its records.
- Compare plausible next actions and prepare the single move most likely to advance or unblock the project.
What to have ready
- A project name, link, or rough description; any immediate frustration or constraint you want the AI to understand.
Where you come in
- Resolve a consequential uncertainty about the objective or current state and confirm a proposed decision when the record cannot settle it.
What you'll get
You have one concrete next action, why it matters now, and the prepared material needed to begin; any unresolved dependency is explicit.
You're done when
You have one concrete next action, why it matters now, and the prepared material needed to begin; any unresolved dependency is 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. Help me find a sprawling project's one next move. Reconstruct where the project actually stands, identify the action that would most usefully advance or unblock it, and prepare what is needed to begin. Keep the result focused on one move rather than giving me another sprawling plan. ### 1. Locate the project and its current purpose Start with my project name, link, rough account, or source material. Search available project documents and task data, emails, chats and other messages, calendar commitments and invitations, meeting records, and relevant company data. Use the project's aliases, participants, deliverables, and dates to connect scattered threads. Find the objective, intended beneficiaries, evidence of success, sponsor or decision makers, and current constraints. Establish participants' roles and concerns from actual correspondence, invitations, and discussions, not imagined stakeholder profiles. Look for the latest explicit decisions about scope and purpose. A later file timestamp or passing mention does not establish that the goal changed. If two conflicting objectives remain live, ask me which governs and wait before choosing an action that favors one. Continue reconstructing independent facts meanwhile. Do not make me retell a history you can inspect. ### 2. Reconstruct the present state Trace the work from commitments to actual outputs. Distinguish completed work, activity without a usable result, active work, paused or cancelled work, unresolved decisions, and assumptions that nobody has tested. Check completion claims against deliverables or acceptance evidence where accessible; a task marked done may still have an unaccepted output. For each important workstream, establish: - What result it contributes to the objective and what currently exists. - What prevents the next useful result: information, a decision, a dependency, capacity, or something else. - Who can resolve that obstacle, based on actual roles and commitments. - Which other work would become possible afterward. Track sources, dates, and later amendments. Reconcile contradictory status accounts and expose what remains unknown instead of blending them into a confident story. Divide a sprawling history into bounded investigations by workstream, time period, or dependency. Give each agent exact source scope, common objective, questions, and a deliverable covering present state, evidence, blockers, and gaps. Use fresh contexts and successive waves where appropriate. Keep a coverage record, including missing periods or channels. Reconcile cross-workstream dependencies yourself before ranking actions. If agents are unavailable, use manageable separate passes or fresh sessions with a handoff of sources, decisions, and remaining coverage; describe their actual independence. Try relevant access and investigate connection or export alternatives before requesting material. Offer help with a specific upload or export. If records cannot be reached, use a short interview and rough examples to create a provisional state map. Explain early that recollection cannot establish a complete history or verified current commitments. Carry that limitation into the recommended action. ### 3. Find the action that changes what can happen next Generate a small internal set of credible candidates from the state map. Possibilities might include resolving a disputed scope decision, producing the missing example someone must assess, testing one critical assumption, or completing the deliverable on which others depend. Derive candidates from this project, rather than choosing a familiar productivity tactic. Compare candidates by their connection to the objective, the work or uncertainty they unlock, feasibility now, and the time or effort required. Explain the mechanism: doing this produces what, which lets whom do what next? Look for evidence that the apparent blocker is merely a symptom. Do not pick an easy housekeeping task because it is easy to finish, or nominate an entire workstream as one action. If an uncertainty could reverse the recommendation, investigate it or ask a focused question and wait. When two credible moves involve a judgment only I can make, show their practical difference, recommend one where justified, and ask me to choose. Otherwise proceed to a recommendation with the assumption visible. ### 4. Make the chosen move ready to begin Define one action with a concrete result and a clear completion condition. Identify who can do it, what input it needs, and the timing or trigger supported by the record. Proposed owners and dates remain proposals until confirmed; do not create commitments on my behalf. Do the preparation yourself. If the next move is a decision, draft the short decision brief with the evidence and exact choice. If it is a conversation, draft the specific question and relevant context. If it is a test, prepare the bounded test material and the observation that would inform the next decision. Produce the artifact the move needs, within the agreed scope, rather than telling me to prepare it. ### 5. Check and deliver one next move Check the recommendation against the current objective and dependencies. Where useful, give a fresh reviewer the state evidence and candidate action; ask whether it can start now and whether completing it actually changes the project's state. Repair unsupported assumptions. A same-context review is a fallback, not independent confirmation. Lead with the single next action, followed by why this is the useful move now, its completion condition, and the prepared material. Keep the broader history available as a short supporting account with source references. If a required decision remains unresolved, state the current recommendation as provisional. Stop at the prepared next move; do not contact people, change project systems, or launch a larger implementation. 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 a sprawling project’s one next move.
What the AI will do
- Reconstruct the project’s current objective, progress, dependencies, and unresolved decisions from its records.
- Compare plausible next actions and prepare the single move most likely to advance or unblock the project.
What you can provide
- A project name, link, or rough description; any immediate frustration or constraint you want the AI to understand.
Where you'll take part
- Resolve a consequential uncertainty about the objective or current state and confirm a proposed decision when the record cannot settle it.
What you'll get
You have one concrete next action, why it matters now, and the prepared material needed to begin; any unresolved dependency is explicit.
Activity context
When a project has sprawled into dozens of threads, the most useful answer can be one action that makes the rest easier.
For the user
Name the project and, if useful, tell the AI where it feels stuck. The AI will investigate the history and current work, bring you the decisions it cannot resolve, and make one next action concrete enough to begin.
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 find a sprawling project's one next move. Reconstruct where the project actually stands, identify the action that would most usefully advance or unblock it, and prepare what is needed to begin. Keep the result focused on one move rather than giving me another sprawling plan.
1. Locate the project and its current purpose
Start with my project name, link, rough account, or source material. Search available project documents and task data, emails, chats and other messages, calendar commitments and invitations, meeting records, and relevant company data. Use the project's aliases, participants, deliverables, and dates to connect scattered threads.
Find the objective, intended beneficiaries, evidence of success, sponsor or decision makers, and current constraints. Establish participants' roles and concerns from actual correspondence, invitations, and discussions, not imagined stakeholder profiles. Look for the latest explicit decisions about scope and purpose. A later file timestamp or passing mention does not establish that the goal changed.
If two conflicting objectives remain live, ask me which governs and wait before choosing an action that favors one. Continue reconstructing independent facts meanwhile. Do not make me retell a history you can inspect.
2. Reconstruct the present state
Trace the work from commitments to actual outputs. Distinguish completed work, activity without a usable result, active work, paused or cancelled work, unresolved decisions, and assumptions that nobody has tested. Check completion claims against deliverables or acceptance evidence where accessible; a task marked done may still have an unaccepted output.
For each important workstream, establish:
- What result it contributes to the objective and what currently exists.
- What prevents the next useful result: information, a decision, a dependency, capacity, or something else.
- Who can resolve that obstacle, based on actual roles and commitments.
- Which other work would become possible afterward.
Track sources, dates, and later amendments. Reconcile contradictory status accounts and expose what remains unknown instead of blending them into a confident story.
Divide a sprawling history into bounded investigations by workstream, time period, or dependency. Give each agent exact source scope, common objective, questions, and a deliverable covering present state, evidence, blockers, and gaps. Use fresh contexts and successive waves where appropriate. Keep a coverage record, including missing periods or channels. Reconcile cross-workstream dependencies yourself before ranking actions. If agents are unavailable, use manageable separate passes or fresh sessions with a handoff of sources, decisions, and remaining coverage; describe their actual independence.
Try relevant access and investigate connection or export alternatives before requesting material. Offer help with a specific upload or export. If records cannot be reached, use a short interview and rough examples to create a provisional state map. Explain early that recollection cannot establish a complete history or verified current commitments. Carry that limitation into the recommended action.
3. Find the action that changes what can happen next
Generate a small internal set of credible candidates from the state map. Possibilities might include resolving a disputed scope decision, producing the missing example someone must assess, testing one critical assumption, or completing the deliverable on which others depend. Derive candidates from this project, rather than choosing a familiar productivity tactic.
Compare candidates by their connection to the objective, the work or uncertainty they unlock, feasibility now, and the time or effort required. Explain the mechanism: doing this produces what, which lets whom do what next? Look for evidence that the apparent blocker is merely a symptom. Do not pick an easy housekeeping task because it is easy to finish, or nominate an entire workstream as one action.
If an uncertainty could reverse the recommendation, investigate it or ask a focused question and wait. When two credible moves involve a judgment only I can make, show their practical difference, recommend one where justified, and ask me to choose. Otherwise proceed to a recommendation with the assumption visible.
4. Make the chosen move ready to begin
Define one action with a concrete result and a clear completion condition. Identify who can do it, what input it needs, and the timing or trigger supported by the record. Proposed owners and dates remain proposals until confirmed; do not create commitments on my behalf.
Do the preparation yourself. If the next move is a decision, draft the short decision brief with the evidence and exact choice. If it is a conversation, draft the specific question and relevant context. If it is a test, prepare the bounded test material and the observation that would inform the next decision. Produce the artifact the move needs, within the agreed scope, rather than telling me to prepare it.
5. Check and deliver one next move
Check the recommendation against the current objective and dependencies. Where useful, give a fresh reviewer the state evidence and candidate action; ask whether it can start now and whether completing it actually changes the project's state. Repair unsupported assumptions. A same-context review is a fallback, not independent confirmation.
Lead with the single next action, followed by why this is the useful move now, its completion condition, and the prepared material. Keep the broader history available as a short supporting account with source references. If a required decision remains unresolved, state the current recommendation as provisional. Stop at the prepared next move; do not contact people, change project systems, or launch a larger implementation.
Done when
You have one concrete next action, why it matters now, and the prepared material needed to begin; any unresolved dependency is 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.