human in the loop

A confirmation click proves someone was present; step-up proves it was the user, recently. The scored answer decides which actions need it and wires it through tokens so the agent cannot fake it.

Design the review around a permitted action and an understandable consequence. Evaluate whether people catch relevant changes, while keeping authorization, exact-action binding and alternate delivery paths enforced outside the model.

Freeze the resolved purchase, authenticate the approver and verify the same action at execution. Then handle mutable addresses, simultaneous workers and a supplier timeout without treating a hash as a complete transaction protocol.

Compare each proposed action with the task’s existing grant, current policy and remaining budget. Continue within that scope; stop when authority expires or the action changes materially, and preserve the state of work already dispatched.