The AI never decides. That is wiring, not a disclaimer.
Sentanis never denies a claim, rejects a demand, contacts a claimant, files with a court, releases a document, or signs anything. For that to mean something, two more things have to hold: the model has to be safe against prompt injection and hallucination, and the claim data has to be secure from the moment it arrives. Each has its own page.
AI safety
Prompt injection and hallucination, engineered against.
How a hostile letter is kept from steering the model, and how a fabricated citation is kept from reaching counsel's signature. Every control named, and the limits stated in the specifications' own words.
- One gateway and one immutable policy for every model call
- Documents, tool results, and prior output enter as labeled evidence
- Seven conditions before a citation can be called verified
- Proofs bound to the exact revision counsel signs
Security
Claim data, from intake to decision.
Seven stages from an independent review of the codebase: who decides, who can open a claim, how it is stored, what leaves the boundary, where generated analysis runs, how a decision is reconstructed, and how failure is detected. Plus what is still being proven.
- Claim-scoped authorization, checked in the application and again in the database
- Field-level encryption and tenant guards in the schema
- A no-network sandbox for generated analysis
- Append-only, content-free audit tied to a named person
Bring your security team to the demo.
We will walk the gateway, the verifier, the access model, and the audit trail on a fictional file, and share the review evidence through a protected channel.