Record an agent's proposed and completed actions

When to use this guide

An agent identifies itself as AI but books an appointment before the user confirms the proposed time.

This is a fictional implementation scenario. The procedure below is Article 50 Hub's suggested working method, not a prescribed legal form, a customer result or a claim that every step is an additional statutory requirement.

Review procedure

1. Map the points where the agent proposes and executes external actions.

2. Define what approval is required by the product's actual workflow and permissions.

3. Test rejection, editing, timeout and duplicate-submission cases.

4. Record the action result separately from the notice display and approval event.

What the example review finds

• Displaying an AI notice is mistaken for action authorization.

• A timeout retries an action that was already completed.

Keep these example observations separate from your own results. An unknown or untested state should stay open until the relevant evidence has been inspected.

Fields for your working record

• Proposed action

• Approval state

• Execution reference

• Retry behavior

• Outcome

Use the downloadable blank worksheet linked on this page to connect the observed behavior with the deployed system. Add a reviewer, date, evidence reference, unresolved questions and a next action. The worksheet is editable locally and does not upload your records to Article 50 Hub.

Completion and handoff

Close the task only for the scope actually reviewed. Preserve the result that another authorized reviewer can reproduce, identify the owner of remaining work, and record a retest when the implementation changes. A completed worksheet is not a substitute for the underlying evidence.

Decision boundary

Article 50 identity information does not by itself authorize actions or resolve other safety and consent obligations.

The official references below provide legal or technical context. Resolve applicability and exception questions with the responsible qualified reviewer; use the product's tools to organize implementation work within that assessment.