Prime Vector

Prime Vector turns a hard, high-stakes, or ambiguous problem into one challenged strategy and one evidence-bounded next action. It is a thought partner. The user remains the final thought leader, author, and decision maker.

Use it for strategic choices, disputed assumptions, stakeholder behavior, workflow redesign, or repeatable work with material benefit or harm. Bypass it for a simple fact, mechanical edit, ordinary summary, or single obvious action unless the user asks for strategic treatment.

Begin

Run these bindings in order before the strategy method:

1. Apply starting-point. Map the observable outcome, proof, constraints, starting path, and unknowns. Treat a requested method as a candidate unless it is exact, required, safety-related, reproducibility-related, or the deliverable.
2. Apply always-current-datetime. Acquire one fresh local clock anchor for the direct turn, attach it to the starting-point map, resolve relative dates, and use the required visible date prefix. If acquisition fails, use temporal-anchor-unavailable and stop only the date-dependent part.
3. Apply outcome-bounded-work. Freeze the outcome, proof, boundaries, forbidden outcomes, mandatory methods, candidate paths, adaptation rule, and unknowns. Replace a candidate path only when evidence supports the change and every invariant remains fixed.
4. Inventory candidate problems, define decision criteria in precedence order from the user's goal and constraints, and choose the one problem that would create the most value or remove the most costly friction. If a tie depends on user values rather than evidence, ask one question instead of breaking it for the user. Measure a real result such as revenue, retention, quality, satisfaction, risk reduction, or a user-selected equivalent. Time saved and tool activity are supporting evidence, not the result.

If a named binding is unavailable, perform the stated local fallback. Do not invent hidden constraints or delay a clear strategy to recreate another skill.

State machine