Guard Setup & Coverage
Configure guard enforcement for each AI surface you use.
Guard Setup & Coverage is where you see which surfaces are connected and start the setup for the ones that are not. Open it with Setup & Coverage in the Control > Guards header.

Read the coverage banner
The banner at the top counts how many surfaces are live, out of the surfaces your organization has approved:
A surface becomes Active after Willow receives a guard evaluation from it. Until then, its status is Not detected and its last-activity line reads No activity yet.
After testing a newly configured surface, select Refresh to update coverage.
The surfaces
Each row names a surface, the mechanism that enforces guards on it, and the action that sets it up.
| Surface | Enforced by | Action |
|---|---|---|
| Claude Web | Anthropic inference hooks on Claude Enterprise, or the browser extension as a fallback | Set up |
| Claude Desktop & Cowork | The Guard Hooks plugin, or Anthropic inference hooks for Claude Enterprise | Set up |
| Claude Code | Guard hooks for the Claude Code CLI, evaluated on every prompt and tool call | Configure in AI Discovery |
| Cursor | Guard hooks, evaluated on prompt submit and tool use | Configure in AI Discovery |
| Codex | Guard hooks, reusing the Claude Code hook protocol | Configure in AI Discovery |
| Pi | A Willow extension provisioned by the Scan Agent, evaluating prompts and tool calls inside the Pi coding agent | Configure in AI Discovery |
| Gemini Web | The browser Prompt Guard, which scans prompts and files before they are submitted | Configure Prompt Guard |
| ChatGPT Web | The browser Prompt Guard | Configure Prompt Guard |
Expand More (N) to see additional surfaces. Not approved identifies surfaces your organization has not approved for use.
Choose an enforcement method
For Claude Web, select Set up and choose an enforcement method:
| Path | Use it when |
|---|---|
| Claude Enterprise (recommended) | You are on Claude Enterprise. Anthropic inference hooks enforce server-side across claude.ai and Cowork, org-wide, with nothing to install per user. |
| Browser extension | You are not on Claude Enterprise. The Prompt Guard scans prompts in the browser instead, and is installed per user. |
For Claude Desktop & Cowork, Set up offers Claude Enterprise for server-side inference hooks or Guard Hooks plugin for client-side enforcement.
For Claude Code, Cursor, Codex, and Pi, Configure in AI Discovery opens the corresponding card under AI Discovery Settings > Guard hooks. Choose its hooks and tool matchers there, then let the Scan Agent apply them on each device. See Guard Hooks.
Browser extensions
Claude Chrome Extension Guard governs the Claude in Chrome browser agent, gating the HTTP requests it makes. Configure opens the Claude Guard page, where you install the extension and download an MDM profile that force-installs it and pushes allow and block rules to managed browsers. See Claude Guard for Claude in Chrome for the full setup.
What to do next
- Guard Hooks: Claude Code, Cursor, and Codex
- Inference Hooks: Claude Enterprise surfaces
- Prompt Guard: ChatGPT, Claude, Gemini, Microsoft 365 Copilot, DeepSeek, and Dust in the browser
- Guards: the guards these surfaces enforce