How to Fact-Check Documents with AI

Ask a general-purpose chatbot to summarize a contract or pull a number out of a report, and you get a fluent answer that sounds right. The problem is the word "sounds." A language model predicts plausible text; plausible and correct are not the same thing. For anything where being wrong has a cost — money, legal terms, medical details — fluency isn't enough. You need answers you can check.

That's the job of Facts mode: answer strictly from sources you trust, and make every claim verifiable.

Grounding: answer from the source, not from memory

A normal chat answers from the model's training. Facts mode answers from your material — the documents you attach, text you paste, or trusted web results you allow. The model is told, in effect: "Here are the sources. Answer from these. If they don't say, say so."

That last clause is the important one. "The documents don't contain that information" is a correct, useful answer — not a failure. A system that would rather invent something than admit a gap is the opposite of trustworthy.

Quotes you can verify

Grounding alone isn't enough, because a model can still paraphrase a source into something it doesn't actually say. So Facts mode goes further: when it makes a factual claim, it can cite an exact quote — and that quote is checked against the source before you see it. If the words really appear in your document, the citation stands. If they don't, the claim is flagged as unverified rather than passed off as fact.

This is a code guarantee, not a promise in a system prompt. The check is a literal text match against what you uploaded:

• The claim is backed by a quote that exists in the source → shown as verified.
• The quote can't be located → shown as unverified, so you know to look closer.

Math that's actually correct

Language models are famously shaky at arithmetic — they predict digits the way they predict words. So when a Facts answer needs to add a column, compute a percentage, or reconcile figures, it doesn't let the model "do the math" in its head. It hands the expression to a real calculator — a safe arithmetic evaluator, not the model's guess — and uses the exact result.

The difference shows up precisely where it matters most: totals, ratios, and reconciliations, where a confident-but-wrong number is worse than no number at all.

What this does and doesn't replace

Facts mode is a research assistant that shows its sources, not an oracle. It's at its best when you want to:

• Pull specific figures or clauses out of a long document.
• Cross-check a claim against text you actually have.
• Get a summary where every key point traces back to a quote.

It is not a substitute for professional judgement on high-stakes decisions. But it changes the question from "do I trust this answer?" to "let me check the quote it gave me" — and that's a question you can actually act on.

The goal isn't an AI that's never wrong. It's an AI whose answers you can verify in seconds.