
70 / 78
Check the claims
Fact-check an AI answer in five minutes before you use it
Pull out the claims, check the ones that would cost you if wrong, and never trust a link you didn't click.
The short answer
To fact-check an AI answer, do three things. First, pull out the specific claims in it: names, numbers, dates, prices, and rules. Second, decide which of those would cost you money or trouble if they were wrong. Third, check those against a source you open yourself, like an official website, the actual document, or the person who would know. For anything you will send, sign, or pay for, that takes about five minutes.
Why AI answers need checking
Chat tools write the likeliest next words. Usually that lands close to the truth. Sometimes it produces a sentence that sounds certain and is simply false. People call that a "hallucination," and it can happen with any tool.
OpenAI's own help pages say it plainly: "ChatGPT can make mistakes. Check important information." That line applies to Claude, Gemini, and every other chat tool too.
Floor vote
How often do you check an AI answer before you use it?
One vote per device. Change it any time.
Loading votes…
Step 1: Ask it to list its own claims
After you get an answer, send this:
List every factual claim in your answer as a numbered list:
names, numbers, dates, prices, laws, and quotes. Next to
each one, say how sure you are and where I could check it.
Now you have a checklist instead of a wall of text.
Step 2: Sort by "what if it's wrong?"
Go down the list and put each claim in one of three piles:
- Would cost money or cause trouble. Prices, deadlines, tax rules, legal steps, medical or safety advice. Check every one.
- Would be embarrassing. A wrong name, a wrong date, a quote from someone famous. Check before you publish or send.
- Background. General explanations you are only using to understand a topic. Skim, don't chase.
The five-minute check
- 01ListEvery claim, numbered
- 02SortCost if it's wrong
- 03OpenThe real source
- 04ClickEvery link
- 05CutWhat you can't confirm
Step 3: Check it against something you can open
- Go to the source. The government website for a rule. The company's own page for a price. The actual contract for what it says.
- Click every link. AI tools sometimes cite pages that don't exist, or that say something different. If the page doesn't say it, the claim doesn't count.
- Search the exact words. Put a quote or a specific phrase in quotation marks on Google. A real quote usually shows up with a named source.
- Check the date. Prices, laws, and app menus change. Look for when the page was last updated.
- Get a second source for numbers. Two places that don't copy each other.
Red flags that mean "check this first"
- Very exact numbers with no source.
- A quote from a famous person.
- A law or rule cited by section number.
- "Experts say" with no names.
- A confident answer about something that happened in the last few weeks.
Using a second AI to help
You can paste the answer into a different chat tool and ask, "What in this is likely to be wrong?" It sometimes catches mistakes. It can also be wrong in the same way. Treat it as a helper that points at what to check, not as the final judge.
The five-minute routine
- Ask for the claim list (1 minute).
- Sort into three piles (1 minute).
- Open sources for the risky pile (3 minutes).
If you can't confirm something that matters, take it out or ask a person who knows. "I couldn't confirm this" is a perfectly good reason to leave a line out.
Field check
Field check
Three questions. Honest answers. No score sent anywhere but this page.
01 / 03
Have you asked an AI to list the claims in its own answer?
Short close
List the claims, check the risky ones against a source you open, and click every link. If you can't confirm it, don't use it.
Keep these
The working rules
AI can sound sure and still be wrong. Then: List the claims; Sort by what a mistake would cost; Check against a source you open; Click every link.