AI product Open source
Agent-Safe Pipeline is a Decionis TypeScript library and runnable reference implementation for routing AI-agent actions through an independent authorization boundary. It captures an agent’s proposed action, target, and parameters as an immutable intent, sends the intent to a Decionis policy gate for an ALLOW, ESCALATE, or BLOCK decision, and coordinates verified human approval followed by policy re-evaluation for escalated actions. Agents cannot authorize their own actions, access downstream privileged credentials, or select trusted handlers.
SafeExecutor accepts only the captured intent and decision, uses a sealed ActionRegistry to map action names to trusted handlers and validate parameters, and consumes a single-use grant bound to the intent before calling an API. The repository includes examples for Shopify refunds, GitHub deployments, procurement, and governed MCP tools, plus canonical-hash conformance vectors and architecture, threat-model, and security-evidence documentation. It is a self-hosted reference implementation rather than a hosted authorization service; its documented safety boundary also depends on provider-side identity, least privilege, network isolation, and incident response. The demos require Node.js 22.14 or later and pnpm 9.
1 use taken from transcripts — each links to the moment in the video.
Prevents an AI agent from approving its own actions by submitting immutable hashed intents to an independent decision-policy layer. Risky actions can require approval tied to the exact intent before credentials are used.
1 in the library.