Sign in
agent-safety

AI agent decision pre-flight: GO / CAUTION / STOP with cryptographic receipt.

AI agent decision pre-flight + action audit + autonomous safety — should agent X execute action Y? Combined check: evidence freshness, provenance trace, policy gate, risk scoring, hallucination signals. Returns GO / CAUTION / STOP / INSUFFICIENT_EVIDENCE with cryptographic receipt. For autonomous agent workflows: tool calls, financial transactions, content publishing, regulatory submissions, multi-step task execution, agent compliance evidence, MCP gateway routing.

post/v2/agent_preflight

Request body

intentstring required

Description of what the agent wants to do

contextobject

Optional agent context (agent_id, session_id, etc.)

Response

Success (synthetic example)

Changes

No recorded changes to this endpoint across all 11 revisions of this API.