By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Managed settings and policy at fleet scale

Managed settings are the admin tier of agent configuration: they sit above user and project files and cannot be overridden locally. Use them to lock permission rules, require managed hooks, restrict MCP servers and plugin marketplaces, pin a minimum client version and force telemetry on. Verify on a device that the policy actually applied.

Read in this order

  1. OfficialDeploy managed settings (Claude Code docs)Start here: delivery options and which keys users cannot override.
  2. OfficialExample settings files (Claude Code docs)Sample settings files you can copy as a starting policy.
  3. OfficialManaged configuration (OpenAI Codex docs)Codex's equivalent, to map one policy to two formats.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.