decionis

decionis

agent-safe-pipeline

97today

Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.

decionis

docker

8717d ago

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.