Content
Pre-Publish Source Check
Inventory the claims before the internet does it for you.
Use when
A factual draft is about to go public.
Cadence
Before publishing factual work
Verification
Every checkable claim is supported by a current source or visibly flagged for an editor.
Structured loop spec
| Field | Value |
|---|---|
| Name | Pre-Publish Source Check |
| Category | Content |
| Trigger | Before publishing factual work |
| Objective | Inventory the claims before the internet does it for you. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | Every checkable claim is supported by a current source or visibly flagged for an editor. |
| 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
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Prompt
Run the Pre-Publish Source Check loop. Use it when A factual draft is about to go public. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when Every checkable claim is supported by a current source or visibly flagged for an editor. or when blocked, budget exhausted, or approval is required.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 "Pre-Publish Source Check" loop from AI Loop Library (https://ailooplibrary.com/loops/prepublish-source-check/) as a bounded loop.
Goal: Inventory the claims before the internet does it for you.
Rules: one change per round; run the same verification every round (Every checkable claim is supported by a current source or visibly flagged for an editor.); append each round to docs/loops/prepublish-source-check/progress.md and update docs/loops/prepublish-source-check/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.