Courts sanction lawyers for citations that do not exist.
In legal work the failure is found by an opponent, in public, with your name on the filing.
Building AI for law firms rather than practicing? Yours is sell into the enterprise.
Three rules a firm actually needs
| Risk | The rule |
|---|---|
| A fabricated citation | a rule requires a citation, and where you supply a lookup function it checks that the citation is found in the source you point it at. An answer that fails either check goes back for a rewrite, or to a person |
| Privilege | material from one matter does not enter a prompt about another. The matter travels on the request, and the wall is a rule every request is checked against, not a folder convention |
| Conflicts | the assistant does not work on a matter the firm is conflicted on, checked at the point of the request, against the conflicts system you already run |
All three are checks on what the model produced. That is a different discipline from the thresholds a bank needs, which is why this page is separate from financial services.
Prove what the AI did
When a client asks whether AI touched their matter, or a court asks how a document was produced, the answer has to be a record, not what someone remembers. Every decision carries the rule that made it and the frozen version it ran on: audit and evidence.
Built for the conflicts review and procurement
On-prem, SSO, layered access control, secrets handling and an append-only audit trail, so the layer running your AI clears the data-handling review a cautious general counsel runs. See security.