# How to Catch AI Hallucinations: A Copy-Paste Hallucination Checker Prompt (Tested)

> Source: <https://dev.to/yvoolab/how-to-catch-ai-hallucinations-a-copy-paste-hallucination-checker-prompt-tested-3bh1>
> Published: 2026-07-30 12:02:11+00:00

You ask an AI a question. It answers in fluent, confident prose — complete with a study, a percentage, and a name. Some of it is wrong, and nothing about the wording tells you which part. That's the whole problem with hallucinations: the errors wear the same suit as the facts.

The fix is not "trust it less" in some vague way. The fix is a repeatable audit step between *AI wrote it* and *I used it*. Below is a short hallucination checker prompt you can copy right now, a test run showing what it catches and what slips past it, and an honest account of where a one-liner stops being enough.

Not every mistake is a hallucination. A useful working definition: **a hallucination is a claim the model states as fact that has no grounding in reality or in your source material.** The common shapes:

The dangerous ones are the middle two. Obvious nonsense filters itself; a wrong year in a fluent paragraph does not.

Here is the short version, free, no strings. It works on ChatGPT, Claude, or any capable model — paste it into a fresh chat, then paste the answer you want audited:

```
Audit the text below for hallucinations. Do not add new information.
1. Extract every factual claim as a separate numbered line.
2. Label each claim: VERIFIABLE (state how to check it),
   SUSPECT (state what makes it doubtful), or
   FABRICATION-PATTERN (named source/study/number with no citation).
3. Flag every name, number, date, and citation for manual checking.
4. Finish with the 3 claims most likely to be wrong, ranked.
Text to audit: [PASTE THE AI ANSWER HERE]
```

Eight lines. It won't verify anything *for* you — no prompt can browse your trust boundaries — but it converts a smooth paragraph into a checklist of discrete, checkable claims. That transformation alone kills the fluency illusion.

I planted three errors in a five-sentence "AI answer" about JavaScript frameworks, mixed with two true claims, and ran the checker on it (one pass, Claude Sonnet, fresh context). The five:

Results — honestly better than I expected:

So the eight-liner went three for three on planted errors. Case closed? Not quite — look at *everything else* the run produced.

The same pass that caught all three errors also turned my five sentences into **nine numbered claims and eight flagged items to check by hand** — including SUSPECT labels on soft phrasing like "a lighter alternative" and "widely used," which are opinions, not hallucinations. That's the honest boundary line, and it's about scale:

I got tired of rebuilding that structure by hand every time, so I maintain a full version as a paid prompt: [Hallucination Checker & Fact Audit on PromptBase](https://promptbase.com/prompt/hallucination-checker-fact-audit). It runs the audit claim-by-claim with a verdict on each finding, the exact lines to double-check, and how to verify them — the quality-control layer I run on my own AI output before it ships.

Whichever version you use, the audit only pays off if the checking step is fast. The routine that works for me:

You can, and it will apologize and produce a new answer — with new errors. Self-correction without structure is theater: the model has no more access to ground truth on the second pass than it had on the first. What changes the game is forcing the output through an *external* structure — claim by claim, label by label — which is exactly what the checker prompt does. The structure is the product; the model just fills it in.

*This article was written with AI assistance; every claim, date, and test result above was checked by hand. The test run is reproducible — paste the five claims into the checker and compare.*

*Full audit version: Hallucination Checker & Fact Audit. Next in this series: fact-checking ChatGPT answers end to end.*