Prompt: fact-check a ChatGPT answer against a source you trust
Paste an AI answer and a source you trust. The AI splits the answer into claims and labels each VERIFIED, WRONG or CAN'T VERIFY, with an exact quote. Tested October 18, 2026 on Claude and GPT-6.1: both caught a planted wrong date.
Works with: ChatGPT, Claude
The task
Check an AI answer (ChatGPT, Claude or any chatbot) against a page, email or document you trust, claim by claim, with proof.
Fact-check the ANSWER below using only the SOURCE below. 1. Split the ANSWER into separate claims, one fact per line. 2. Give each claim one label: VERIFIED = the SOURCE says the same thing. WRONG = the SOURCE says something different. CAN'T VERIFY = the SOURCE doesn't say. 3. For each label, quote the exact words from the SOURCE. No quote, no VERIFIED. 4. For each WRONG claim, write the corrected version, using only the SOURCE. Do not use outside knowledge. Do not add new facts. Answer as a table: Claim | Label | Exact quote from the SOURCE | Fix ANSWER: [PASTE THE AI ANSWER] SOURCE: [PASTE THE PAGE, EMAIL OR DOCUMENT YOU TRUST]
How to use it
- Paste the AI's answer under ANSWER, as it is.
- Paste the page, email or document you trust under SOURCE. Not another AI answer.
- No document? Ask the AI for a link per claim, open each link, and paste the paragraph that matters.
- Search your source for each quote (Ctrl+F or Cmd+F). No quote found, not verified.
What you get
A table with one row per claim: VERIFIED, WRONG or CAN'T VERIFY, the exact quote from your source, and a fix for every WRONG claim. In our test (October 18, 2026), Claude Opus 5.5 and GPT-6.1 via OpenAI Codex both caught the wrong date (Friday, October 30 instead of Thursday, October 29), verified the deadline word for word and marked the chaperone line CAN'T VERIFY.
| Claim | Label | Exact quote from the SOURCE | Fix | |---|---|---|---| | The trip is for Grade 4. | VERIFIED | "Our Grade 4 classes will visit the science centre" | — | | The trip is to the science centre. | VERIFIED | "Our Grade 4 classes will visit the science centre" | — | | The trip is on Friday, October 30. | WRONG | "will visit the science centre on Thursday, October 29" | The trip is on Thursday, October 29. | | The signed permission slip is due Monday, October 26. | VERIFIED | "Please send back the signed permission slip and $12 by Monday, October 26." | — | | $12 is due Monday, October 26. | VERIFIED | "Please send back the signed permission slip and $12 by Monday, October 26." | — | | Parents are welcome to come along as volunteer chaperones. | CAN'T VERIFY | None. The SOURCE doesn't mention parents coming along, volunteers or chaperones. | — |
Go further
- Prompt: make the AI check its own draft against your rulesPaste a draft and your rules; the AI lists every rule the draft breaks, then rewrites it. Tested on a generic template: it flagged the invented content, the missing facts and all 14 placeholders.See the prompt
- Prompt: the 5-part brief that fixes vague ChatGPT answersWho, task, facts, rules, format, plus one line that makes the AI ask before it guesses. Works for client emails, replies and everyday messages. Tested for real: a one-liner gave a template with 14 blanks, the brief gave a ready email.See the prompt
- How to fact-check ChatGPT answers: a copyable source-check prompt (tested on 2 AIs)ChatGPT can sound sure and still be wrong. This copyable prompt checks any AI answer against a source you trust and labels each claim VERIFIED, WRONG or CAN'T VERIFY, with an exact quote. Our October 18, 2026 test: Claude and GPT-6.1 both caught a planted wrong date.Read the article
Where should you start with AI?
The free assessment gives you, in 4 minutes, the 3 tasks to automate first in your business.