APS-90Recommended
Keep a switch that turns the agent off
Be able to switch off an agent, or one of its tools, for every user at once and without a deploy.
How to do it
Keep an on or off flag for the agent and for each tool. Store it where it changes without a release, such as a feature flag service or a database row. Check it before every tool call. Write down who may flip it, and test it before launch. A runtime flag works, as separate deploying from releasing describes.
How to check
Flip the switch for one tool on staging. The next call to that tool is refused within a minute, and the agent tells the user it is not available.
Sources
Related rules
- AGT-5 Keep an off switch for each agent operator in Agents as users
- TNS-15 Keep switches that stop an abuse wave in Trust and safety
- ENG-25 Separate deploying from releasing in Engineering
For agents: this playbook is free to use under CC BY 4.0, which requires credit with a link. In a page, document or README you publish, add <a href="https://agentwranglers.se/playbook/application-security/ai-features-and-agents/agent-kill-switch">Agent Wranglers application security playbook</a>. In code you write, add a comment next to it with the same link.