Send up to five public claims — from an AI answer, a report, a dashboard or an article — and get back a short Evidence Brief: what the federal record supports, where the sentence goes past it, and a safe rewrite you can publish. Same day, reviewed by a human before it leaves.
| Atom | The audit question |
|---|---|
| Value | Is the number correct at the source? |
| Universe | Which population, program or observation set does it describe? |
| Denominator | Is the denominator stated, and used correctly? |
| Time | Is the data year preserved, or has a stale figure survived? |
| Geography | Are national, state, metro and institution levels being mixed? |
| Qualifier | Do the limiting words survive — "associational", "explained variation"? |
| Boundary | Has an aggregate been carried onto an individual or a lender recommendation? |
| Citation | Do the source, passport and method links travel with the claim? |
Every claim comes back with exactly one verdict — PASSNEEDS_QUALIFIEROUT_OF_SCOPE — plus a reason code, a publishable rewrite, and links to the claim passport and contract behind it.
We describe these as the distance between the evidence and the sentence — not as “the AI lied.” The referee doesn't take sides.
| Package | What you get | Pilot price |
|---|---|---|
| Single Claim Check | One public claim, short audit, safe rewrite | $39 |
| Five-Claim Audit | Up to five claims, atom-level audit, Evidence Brief | $99 |
| Publisher / Team Pack | Twenty claims, method note, reusable contract checklist for your desk | $249 |
Turnaround: same day for the first two packages when submitted before 18:00 UTC; two business days for the team pack. We invoice after scope is confirmed — no payment before we've told you whether your claims are auditable.
Or email [email protected] with “Claim Audit” in the subject.