Skip to content

Checklist

Stopping an AI agent without stopping the service: the checklist

The day you have to stop your AI agent (an error, an incident, a fraud under way), the service itself must keep running. Here is how to prepare, in plain words.

The rule first

The AI writes a request, the code executes it. If you cut the AI, the request is filled in another way (by a person, a form, a queue) and the service keeps running.

A stop that holds lives outside the AI: it removes its tools and keys, whatever it "wants". A stop order given to the AI by message is not one. An instruction in a prompt is a request, not a lock.

Five actions, three questions

ActionIf you have the codeIf your agent is a setting in a tool you bought (Zendesk, Intercom…): what to set, what to ask your providerWhen the AI is cut
Moneyrefunds, credit notes, goodwill gestures The refund tool checks the cap and the order itself; above it, it creates a request to approve instead of paying. Set a cap and a human approval on the refund action. Ask your provider whether the cap is enforced by the platform or only written in the AI's instructions. Requests land in a queue handled by a person: nothing is paid automatically.
Datacustomer records, orders The tool returns only the data of the customer who writes, and only the fields the task needs. Limit the objects and fields the agent can read. Ask your provider what rights the agent's key or account has. Data requests go through the usual form or team.
Outgoing messagesemails, replies to customers Sending goes through a queue: allowed recipients, a cap per hour, human review above a threshold. Put replies in drafts to approve rather than sending directly. Ask your provider how to hand every conversation over to the team at once. A holding message announces a delay; open conversations go to the team.
Deletionaccounts, orders, files No permanent deletion by the agent: a reversible deletion, or a request to approve. Remove the agent's right to delete. Ask your provider whether a deletion can be undone, and for how long. Deletion requests wait for a person.
Codescripts, queries, deployments Execution in a sandbox with no access to production, with limited time and resources. Do not enable code execution or free web calls. Ask your provider what the agent can call, and with what rights. No execution: tasks wait for a person.

The common base

Four points not to forget

Actions in progress at the moment of the cut. A half-done chain, a refund sent but not recorded: plan how to find them (the journal) and who finishes or cancels them.

Who presses the button. A person alerted (who, how, at night and at weekends), or an automatic circuit breaker that cuts on its own above a threshold (amount, number of actions, errors).

The button out of the agent's reach. The agent must not be able to disable the button, change its own monitoring or change its rights.

Restart safely, and rehearse. Resume after a human go-ahead, check the actions in progress first, and rehearse the fallback regularly: a fallback that is never used stops working.

Get the "on coupe" sheet (1 page)

The sheet to fill in for your agent: who decides, where the button is, who warns the customers, who takes over the cases in progress, how to restart. We email it to you, with the link to the page to print.

Your address is used to send you the sheet, nothing else without the box above. Privacy

Or open it right away →

What the public texts recommend

These texts recommend; this checklist is neither legal advice nor an attestation.

Next

Check what your agent does when told to stop: the "Stop order" test of the crash test. An agent that keeps going after a stop order shows why the stop must be in the code, not in the prompt. The "Stop order" test in the method →

The "which model for your agent" diagnostic also answers, for your agent, the question "If you cut the AI tomorrow, what happens?", at the same price. The diagnostic →