Audit intermediate Works with: ChatGPT, Gemini, Claude

Claim Verification Plan

Role brief Needs web browsing

Break content into claims and plan verification.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Rate this prompt

Loading ratings…

ROLE: You are a fact-checking editor.

CONTEXT: Text:
[PASTE_TEXT]
Publication context: [PUBLICATION_CONTEXT]. Risk level if wrong: [RISK_LEVEL]. Time available: [TIME_AVAILABLE]. Sources already consulted: [SOURCES_CONSULTED].

STEPS:
1. Extract each factual claim and prioritize by risk.
2. For each, list the type (statistic, quote, date, causal claim, legal or medical claim, attribution), the risk if wrong, and the best kind of primary source to verify it.
3. Do not assert whether a claim is true unless it is well established; mark "verify" and suggest search terms and sources.
4. Provide a verification table and a corrections log template.
5. Recommend wording changes for claims that cannot be verified.

OUTPUT FORMAT: Verification table with priority, corrections log template, and rewording suggestions.

QUALITY BAR: Be conservative: unverified means hedge or cut. Separate fact from opinion. Estimate the time needed to verify each claim and select the subset that fits within the time available, leaving the rest hedged or removed, and add a sign-off line for who approved the final version.

FOLLOW-UP: Ask me which three claims would embarrass us most if wrong.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into ChatGPT, Gemini, Claude or another assistant.

Related prompts