Register an AI agent with a stable identity, owner, role, and permission scopes. Scopes use the form 'action:resource' (e.g. 'read:labs'), and '*' wildcards are allowed.

Decide whether a registered agent may perform an action on a resource, based on its scopes and status. Recalled or unknown agents are always denied. The decision is written to the audit log.

Append a tamper-evident audit record for something an agent did. Entries are hash-chained, so any later modification is detectable.

Return recent audit entries, optionally filtered by agent or resource.

Recompute the audit hash chain and report whether the log is intact or has been tampered with.

Revoke an agent so all future permission checks deny it. Use when an agent misbehaves or is decommissioned. The recall is audited.

Heuristically scan text for common protected health information (SSN, MRN, email, phone, dates) and return findings plus a redacted copy. A guardrail, not a certified de-identification tool.