Governed agent execution

We need agents to act without granting ambient authority

Consequential action must pass through external controls sized to the accepted blast radius.

An agent that inherits a broad service account can turn one mistaken or manipulated decision into an unrestricted external effect. A system prompt may describe what the agent should do, but it cannot enforce which identity acts, which resource is in scope, when authority expires, or whether the action should pause.

See the Governed Agent Execution pillar →

Decisions that constrain useful action

  1. Identity: Preserve the initiating principal and the service identity that will execute the action.
  2. Delegation: Grant task-bound authority with explicit purpose, resources, limits, and expiry instead of standing ambient access.
  3. Policy: Evaluate actor, action, resource, environment, and risk outside the model before execution.
  4. Containment: Restrict filesystem, network, credentials, data, time, and spend according to the worst accepted effect.
  5. Escalation and evidence: Make approvals specific and preserve the policy, authority, request, outcome, and resulting state.

Read the authority path

Proof and limits


Inspect policy-as-code

See how one bounded implementation turns governance rules into deterministic runtime outcomes and attributable evidence.