A public-safe research prototype for controlling AI-agent tool actions with deterministic policy, risk-based human approval, time-bound authorization and a tamper-evident audit chain.
Deterministic policy enforcement for AI agent tool calls. It evaluates every tool call against user-defined rules before execution, with no LLM in the authorization path.
Enables language models to query a clinical relational database through a small set of validated, row-capped tools, with evaluation of answerability and data leakage.
Provides permission gates and tamper-evident audit logging for AI agent tool executions, with declarative policies, consent ladders, and hash-chained verification.