Ratia offers two engagements. Both measure a legal-AI tool's output against the court-adjudicated record. Both are delivered as the Ratia Report — a document a partner, a carrier, or an ethics panel can read.
Evaluating a legal-AI tool before you commit? We test it against court-adjudicated ground truth so you choose on measured grounding — not on the demo. You give us the tool, the jurisdiction, and a representative slice of research queries. We give you back a scorecard on how the tool actually performs when its output meets the record.
Your firm already relies on AI in research, drafting, and review. We audit what it's actually doing on your jurisdiction's law, on the kind of matters you work — before a court finds out for you. Delivered as a snapshot dated to the tool version and jurisdictional corpus tested.
Every engagement delivers the same document. Not a certification. Not legal advice. A measurement — inspectable, criticizable, replicable.
How the tool performed on each check — existence, holding, validity — reported by court level, never blended into one flattering number.
How the tool fails when it fails: invented cases, misread holdings, dead law cited as good. The section that tells you what you're actually risking.
Blind scoring, independent attorney review, ground truth anchored to the court's own words at the pincite. Built to survive an expert's cross-examination.
Read the full methodology — how the three checks are operationalized, how ground truth is built for Minnesota, how blind scoring and inter-rater reliability work. Also as a downloadable PDF (23 pp).
On the list. You'll see the Minnesota results first.
Something went wrong — please try again.
Early access is opening to a small group of design partners.