---
title: "Keep a switch that turns the agent off · Agent Wranglers"
url: https://agentwranglers.se/playbook/application-security/ai-features-and-agents/agent-kill-switch
id: APS-90
level: Recommended
applies: ai-features
updated: 2026-10-27
build: a2a6bdfed830
tokens: 677
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Keep a switch that turns the agent off

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

- ID: APS-90
- Level: Recommended
- Chapter: [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md)
- Rule: Be able to switch off an agent, or one of its tools, for every user at once and without a deploy.
- 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.
- Applies when: The project uses AI models.
- How: 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](https://agentwranglers.se/playbook/engineering/running-in-production/deploy-is-not-release.md) describes.

## Sources

- [NIST AI Risk Management Framework 1.0, MANAGE 2.4](https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.100-1.pdf)

## Related rules

- AGT-5 [Keep an off switch for each agent operator](https://agentwranglers.se/playbook/agents-as-users/identifying-agents/operator-kill-switch.md) in Agents as users
- TNS-15 [Keep switches that stop an abuse wave](https://agentwranglers.se/playbook/trust-and-safety/running-trust-and-safety/abuse-switches.md) in Trust and safety
- ENG-25 [Separate deploying from releasing](https://agentwranglers.se/playbook/engineering/running-in-production/deploy-is-not-release.md) in Engineering

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/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.

- Previous: [Send models only the private data they need](https://agentwranglers.se/playbook/application-security/ai-features-and-agents/private-data-to-models.md)
- Next: [Run code the model writes in a sandbox](https://agentwranglers.se/playbook/application-security/ai-features-and-agents/sandbox-model-code.md)
- [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md)