AI writes confident sentences whether or not they're true. Paste the answer and it pulls out every checkable claim — figures, dates, names, citations, absolutes — and gives you a tick list. Mark each verified, wrong or unverifiable, and the risk score updates.
Nothing saved yetYour inputs are kept in this browser only — nothing is sent anywhere.
Claims
What gets flagged. Sentences containing a number, percentage or amount; a year or date; a citation or study reference; a proper noun that looks like an organisation or person; a superlative or absolute (“always”, “never”, “the largest”, “all”); or a hedge that hides an unverified claim (“studies show”, “it is widely known”). It's a prompt to check, not a judgement — a flagged sentence isn't wrong, it's just one you shouldn't take on trust.