> ## Documentation Index
> Fetch the complete documentation index at: https://docs.duvo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Team Guardrails

> Set a team-wide policy that every Agent must follow.

Team Guardrails let administrators define a team-wide policy that every Agent in the team must follow. Go to **Settings → Guardrails** to configure them. Only team Administrators and Owners can view and edit guardrails.

***

## Guardrails text

An optional free-text policy prepended to every Agent's system prompt. Use it to set ground rules that apply across all agents — for example, tone requirements, data handling rules, or escalation instructions.

***

## Saving changes

Click **Save guardrails** after editing. Changes take effect on the next Run — agents already running are not affected mid-run. Guardrails revisions are tracked in the revisions panel below the editor.

***

## Blocked domains

Blocked domains are now managed under **Settings → Browsing**. See [Team Browsing](/user-guide/teams/browsing) for details.

***

## Related

* [Team Browsing](/user-guide/teams/browsing) — Blocked domains
* [Roles and Permissions](/user-guide/teams/roles-and-permissions) — Who can view and edit guardrails
* [Guardrails for High-Risk Automations](/user-guide/security/high-risk-guardrails) — Best-practice patterns for HITL gates, caps, and allow/deny lists
* [Browsing Capabilities](/user-guide/assignment-features/browsing) — How agents browse the web