Content
Recurring Question to FAQ
Convert repeated confusion into one reusable answer instead of playing inbox whack-a-mole with nicer fonts.
Use when
People keep asking the same product, pricing, setup, troubleshooting, or workflow question and the answer is scattered across notes, docs, Slack, or someone's head.
Beginnerdifficulty
Contentcategory
Mia daily expansionsource
Cadence
Weekly, or whenever the same question appears three times across email, chat, calls, comments, or onboarding
Verification
The loop produces a source-backed answer, suggested placement, support macro, and measurement hook; nothing is published, sent, or promised externally without approval.
Structured loop spec
| Field | Value |
|---|---|
| Name | Recurring Question to FAQ |
| Category | Content |
| Trigger | Weekly, or whenever the same question appears three times across email, chat, calls, comments, or onboarding |
| Objective | Convert repeated confusion into one reusable answer instead of playing inbox whack-a-mole with nicer fonts. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Gather recent examples of the repeated question from support tickets, emails, calls, comments, onboarding notes, search queries, and internal messages.; Cluster the examples by user intent, wording, segment, urgency, and source of confusion; discard one-off edge cases unless they expose a safety or trust risk.; Find the canonical answer in product docs, policies, code behavior, pricing pages, release notes, or owner confirmation; mark gaps and assumptions explicitly.; Draft a concise FAQ answer, optional longer help-doc section, and support macro with scope, caveats, links, and a clear escalation path.; Recommend where the answer should live and how to measure whether it works, such as fewer repeat tickets, better search hits, onboarding completion, or lower reply time.; Queue any external publish, customer send, pricing statement, policy claim, legal/security wording, or product commitment for human approval before it goes live. |
| Verification | The loop produces a source-backed answer, suggested placement, support macro, and measurement hook; nothing is published, sent, or promised externally without approval. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
Steps
- Gather recent examples of the repeated question from support tickets, emails, calls, comments, onboarding notes, search queries, and internal messages.
- Cluster the examples by user intent, wording, segment, urgency, and source of confusion; discard one-off edge cases unless they expose a safety or trust risk.
- Find the canonical answer in product docs, policies, code behavior, pricing pages, release notes, or owner confirmation; mark gaps and assumptions explicitly.
- Draft a concise FAQ answer, optional longer help-doc section, and support macro with scope, caveats, links, and a clear escalation path.
- Recommend where the answer should live and how to measure whether it works, such as fewer repeat tickets, better search hits, onboarding completion, or lower reply time.
- Queue any external publish, customer send, pricing statement, policy claim, legal/security wording, or product commitment for human approval before it goes live.
Prompt
Run the Recurring Question to FAQ loop. Gather recent instances of the repeated question across support tickets, emails, calls, comments, onboarding notes, search queries, and internal messages. Cluster them by intent, wording, segment, urgency, and source of confusion. Identify the canonical answer from docs, policies, product behavior, pricing pages, release notes, or owner confirmation, and label any assumptions or gaps. Draft a concise FAQ entry, optional longer help-doc section, and support macro with caveats, links, and escalation path. Recommend placement and a measurement hook. Do not publish, send to customers, quote pricing, make policy/legal/security claims, or promise product changes without approval.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Recurring Question to FAQ" loop from AI Loop Library (https://ailooplibrary.com/loops/recurring-question-to-faq/) as a bounded loop.
Goal: Convert repeated confusion into one reusable answer instead of playing inbox whack-a-mole with nicer fonts.
Rules: one change per round; run the same verification every round (The loop produces a source-backed answer, suggested placement, support macro, and measurement hook; nothing is published, sent, or promised externally without approval.); append each round to docs/loops/recurring-question-to-faq/progress.md and update docs/loops/recurring-question-to-faq/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.