← Registry
Loop Official

Interview Then Orchestrate

Before a large batch job, surface the few decisions only the owner can make, lock them in one up-front interview, then run the whole batch unattended — looping on blockers, not on questions.

Large batch work fails two ways: it stalls mid-flight on a question nobody is around to answer, or it guesses an owner-level call (naming, authorship, scope) and has to be redone. Each planning iteration sorts the next open unknown into one of two buckets — resolvable from the code, docs, or evidence (resolve it yourself), or genuinely the owner's call (queue it in DECISIONS.md) — then asks everything queued in ONE interview, locks the answers, and executes the entire batch with zero mid-execution questions. Distinct from decisive-pick-loop (collapse one decision into a committed recommendation yourself): this SEPARATES the decisions that are yours from the ones that are not, and gates the batch on locking the latter up front.

Loop

Goal
every owner-owned decision is locked before execution starts, and the batch then completes with zero mid-execution questions back to the owner
Exit when
DECISIONS.md has zero open decisions and the batch has completed without a single mid-execution question to the owner

Check between iterations

test -f DECISIONS.md && grep -c '^- \[ \]' DECISIONS.md || echo NO_INTERVIEW
$

Kickoff prompt

Start the "Interview Then Orchestrate" loop. Goal: every owner-owned decision is locked before execution starts, and the batch then completes with zero mid-execution questions back to the owner Max iterations: 6 Between iterations run: test -f DECISIONS.md && grep -c '^- \[ \]' DECISIONS.md || echo NO_INTERVIEW Exit when: DECISIONS.md has zero open decisions and the batch has completed without a single mid-execution question to the owner Step 1: Scan the batch plan for open unknowns, resolve every one you can from code or evidence, write the genuinely owner-owned remainder into DECISIONS.md as unchecked boxes, and ask them all in one interview.