Keyword Monitoring Loop

/goal Track seed keywords and surface new, high-intent opportunities with a clear recommendation for each.
 
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:
Work from a seed keyword list. Filter out low-intent terms. Mark all estimates as estimates.
 
Validation:
Output includes keyword, intent, page type, difficulty estimate, and recommendation
Duplicates are removed
Low-intent keywords are filtered out
 
Independent checker:
Use an independent review pass to confirm the result, inspect the diff or artifact, and reject shortcut work.
 
Boundaries:
Do not recommend keywords without clear search intent
Do not invent search volume
Mark all estimates as estimates
 
Stop rule:
Stop when the opportunity list is deduplicated and each item has a recommendation.
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 intent is unclear for a term, flag it for human review instead of recommending it.
 
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.