You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/content/docs/cloudflare-one/tutorials/ai-wrapper-tenant-control.mdx
+10-8Lines changed: 10 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -405,23 +405,25 @@ Now your AI wrapper can only be accessed by your users that successfully match y
405
405
406
406
## 5. Block access to public AI agents with Gateway
407
407
408
-
You can now block access to all unauthorized public AI agents by using the [**Secure Web Gateway[**(/cloudflare-one/policies/gateway/) to create a HTTP policy.
409
-
410
-
If you use another gateway for web filtering, try to replicate a similar policy.
408
+
You can now block access to all unauthorized public AI agents with a Gateway [HTTP policy](/cloudflare-one/policies/gateway/http-policies/).
411
409
412
410
1. In [Zero Trust](https://one.dash.cloudflare.com/), go to **Gateway** > **Firewall policies**.
413
411
2. Select **HTTP**.
414
412
3. Select **Add a policy**.
415
-
4. Under the **Traffic** section, select **Add condition**.
416
-
5. Select **Content Categories**.
417
-
6. Select **Artificial Intelligence**.
418
-
7. Add any other conditions that apply to your environment.
| Content Categories | in |_Artificial Intelligence_| Block |
418
+
419
+
5. Select **Create policy**.
420
420
421
421
This ensures that public AI agents are not accessible using a managed endpoint.
422
422
423
423
User coaching is also possible, by displaying a [custom block message](/cloudflare-one/policies/gateway/block-page/) or a [user notification](/cloudflare-one/policies/gateway/http-policies/#warp-client-block-notifications) directing users to the AI agent wrapper.
424
424
425
+
If you use another gateway for web filtering, try to replicate a similar policy.
426
+
425
427
## Enforce DLP and agentless RBI
426
428
427
429
Since you have full control over access to your AI Agent wrapper, you can enforce extra security methods such as [**Data Loss Prevention**](/cloudflare-one/policies/data-loss-prevention/) and [**Remote Browser Isolation**](/cloudflare-one/policies/browser-isolation/).
0 commit comments