Research Summary Loop

/goal Synthesize multiple sources into a structured brief that separates facts, assumptions, and recommendations.
 
Work toward this goal until all validation checks pass or the stop rule is reached.
 
Loop cycle:
1. Discovery — Read the latest signal for this template before acting: CI output, issue detail, review comment, dataset report, or content brief.
2. Handoff — Hand the work to one agent in an isolated branch, worktree, or clearly scoped session. Keep final approval with a human.
3. Verification — Use an independent review pass to confirm the result, inspect the diff or artifact, and reject shortcut work.
4. Persistence — Save a short run note with the signal reviewed, actions taken, validation result, and next recommended step.
5. Scheduling — Run manually until the loop is reliable; only then consider a scheduled or event-triggered run.
 
Context:
Cite a source for every factual claim. Flag contradictions. Do not fabricate citations.
 
Validation:
Every factual claim has a source note
Contradictions are flagged
Summary separates facts, assumptions, and recommendations
 
Independent checker:
Use an independent review pass to confirm the result, inspect the diff or artifact, and reject shortcut work.
 
Boundaries:
Do not fabricate citations
Do not over-quote sources
Do not hide uncertainty
 
Stop rule:
Stop when every claim is sourced and the brief separates facts, assumptions, and recommendations.
Maximum iterations: 3
 
Budget:
Stop before exceeding the agreed per-run token budget.
 
Human approval:
Required before merge, deploy, delete, purchase, or external communication.
 
Fallback:
If sources conflict or cannot be verified, present the uncertainty rather than resolving it arbitrarily.
 
Do not delete tests, bypass checks, or modify unrelated files just to satisfy the validation condition. If blocked, stop and summarize the blocker, attempted fixes, and recommended next action.