Use casesAction authorization
06

Action authorization

Guard the one-way door in any agent workflow.

Let AI prepare the work, then put a deterministic or human decision before the refund, invoice approval, payout, booking, account change, or other irreversible commit.

Trigger

An agent proposes a consequential action through an SDK, tool wrapper, gateway, or API adapter.

What breaks

The final answer looks reasonable, but an intermediate tool call crosses a policy boundary, lacks trusted evidence, or exceeds the authority the principal granted.

Control point

Create a typed proposed action, evaluate authority and evidence, then authorize, hold for approval, or deny before the existing system executes it.
01Proposed action
02Policy + evidence
03Decision
04Existing system

How it works

  1. 01
    Describe

    Make the action explicit

    Send the operation, amount, principal, counterparty, grant, evidence references, and idempotency key as a typed action.

  2. 02
    Decide

    Evaluate facts outside the prompt

    Deterministic policy checks the action against caps, spend windows, required evidence, known counterparties, and approval thresholds.

  3. 03
    Escalate

    Hold the ambiguous cases

    A held action does not execute. It waits for the named approver, and the approval or denial becomes part of the record.

  4. 04
    Prove

    Join decision to execution

    The decision receipt explains what was allowed. The execution receipt records what actually moved after authorization.