" \
+--json '{ "prompt": "Provide the phone number for the person associated with example@example.com" }'
+```
+
+The PII category for this request would be `EMAIL_ADDRESS`.
+
+## 5. Review labeled traffic and detection behavior
+
+Use [Security Analytics](/waf/analytics/security-analytics/) in the new application security dashboard to validate that the WAF is correctly labeling traffic for the endpoint.
+
+1. In the Cloudflare dashboard, go to the **Analytics** page.
+
+
+
+2. Filter data by the `cf-llm` managed endpoint label.
+
+ | Field | Operator | Value |
+ | ---------------------- | -------- | -------- |
+ | Managed Endpoint Label | equals | `cf-llm` |
+
+3. Review the detection results on your traffic. Expand each line in **Sampled logs** and check the values in the **Analyses** column. Most of the incoming traffic will probably be clean (not harmful).
+
+4. Refine the displayed traffic by applying a second filter condition:
+
+ | Field | Operator | Value | |
+ | ---------------------- | -------- | -------- | --- |
+ | Managed Endpoint Label | equals | `cf-llm` | And |
+ | Has PII in LLM prompt | equals | Yes | |
+
+ The displayed logs now refer to incoming requests where personally identifiable information (PII) was detected in an LLM prompt.
+
+Alternatively, you can also create a custom rule with a _Log_ action (only available on Enterprise plans) to check for potentially harmful traffic related to LLM prompts. This rule will generate [security events](/waf/analytics/security-events/) that will allow you to validate your Firewall For AI configuration.
+
+## 6. Mitigate harmful requests
+
+[Create a custom rule](/waf/custom-rules/create-dashboard/) that blocks requests where Cloudflare detected personally identifiable information (PII) in the incoming request (as part of an LLM prompt), returning a custom JSON body:
+
+- **When incoming requests match**:
+
+ | Field | Operator | Value |
+ | ---------------- | -------- | ----- |
+ | LLM PII Detected | equals | True |
+
+ If you use the Expression Editor, enter the following expression:
+ `(cf.llm.prompt.pii_detected)`
+
+- **Rule action**: Block
+- **With response type**: Custom JSON
+- **Response body**: `{ "error": "Your request was blocked. Please rephrase your request." }`
+
+For additional examples, refer to [Example mitigation rules](/waf/detections/firewall-for-ai/example-rules/). For a list of fields provided by Firewall for AI, refer to [Firewall for AI fields](/waf/detections/firewall-for-ai/fields/).
+
+
+
+You can combine the previous expression with other [fields](/ruleset-engine/rules-language/fields/) and [functions](/ruleset-engine/rules-language/functions/) of the Rules language. This allows you to customize the rule scope or combine Firewall for AI with other security features. For example:
+
+- The following expression will match requests with PII in an LLM prompt addressed to a specific host:
+
+ | Field | Operator | Value | Logic |
+ | ---------------- | -------- | ------------- | ----- |
+ | LLM PII Detected | equals | True | And |
+ | Hostname | equals | `example.com` | |
+
+ Expression when using the editor:
+ `(cf.llm.prompt.pii_detected and http.host == "example.com")`
+
+- The following expression will match requests coming from bots that include PII in an LLM prompt:
+
+ | Field | Operator | Value | Logic |
+ | ---------------- | --------- | ----- | ----- |
+ | LLM PII Detected | equals | True | And |
+ | Bot Score | less than | `10` | |
+
+ Expression when using the editor:
+ `(cf.llm.prompt.pii_detected and cf.bot_management.score lt 10)`
+
+
diff --git a/src/content/docs/waf/detections/firewall-for-ai/index.mdx b/src/content/docs/waf/detections/firewall-for-ai/index.mdx
new file mode 100644
index 000000000000000..4bf0cb728e4a71d
--- /dev/null
+++ b/src/content/docs/waf/detections/firewall-for-ai/index.mdx
@@ -0,0 +1,42 @@
+---
+pcx_content_type: concept
+title: Firewall for AI (beta)
+tags:
+ - AI
+sidebar:
+ order: 5
+ group:
+ label: Firewall for AI
+ badge:
+ text: Beta
+---
+
+import {
+ GlossaryTooltip,
+ Tabs,
+ TabItem,
+ Details,
+ Steps,
+ Type,
+ DashButton,
+ Render,
+} from "~/components";
+
+Firewall for AI is a detection that can help protect your services powered by large language models (LLMs) against abuse. This model-agnostic detection currently helps you do the following:
+
+- Prevent data leaks of personally identifiable information (PII) — for example, phone numbers, email addresses, social security numbers, and credit card numbers.
+- Detect and moderate unsafe or harmful prompts – for example, prompts potentially related to violent crimes.
+- Detect prompts intentionally designed to subvert the intended behavior of the LLM as specified by the developer – for example, prompt injection attacks.
+
+When enabled, the detection runs on incoming traffic, searching for any LLM prompts attempting to exploit the model. Currently, the detection only handles requests with a JSON content type (`application/json`).
+
+Cloudflare will populate the existing [Firewall for AI fields](/waf/detections/firewall-for-ai/fields/) based on the scan results. You can check these results in the [Security Analytics](/waf/analytics/security-analytics/) dashboard by filtering on the `cf-llm` [managed endpoint label](/api-shield/management-and-monitoring/endpoint-labels/) and reviewing the detection results on your traffic. Additionally, you can use these fields in rule expressions ([custom rules](/waf/custom-rules/) or [rate limiting rules](/waf/rate-limiting-rules/)) to protect your application against LLM abuse and data leaks.
+
+## Availability
+
+Firewall for AI is available in closed beta to Enterprise customers proxying traffic containing LLM prompts through Cloudflare. Contact your account team to get access.
+
+## More resources
+
+- [Cloudflare AI Gateway](/ai-gateway/)
+- [Learning Center: What are the OWASP Top 10 risks for LLMs?](https://www.cloudflare.com/learning/ai/owasp-top-10-risks-for-llms/)
diff --git a/src/content/partials/api-shield/labels-add.mdx b/src/content/partials/api-shield/labels-add.mdx
new file mode 100644
index 000000000000000..27708c14ef5a08a
--- /dev/null
+++ b/src/content/partials/api-shield/labels-add.mdx
@@ -0,0 +1,27 @@
+---
+params:
+ - labelName?
+---
+
+import { DashButton, Markdown } from "~/components";
+
+{/* prettier-ignore-start */}
+
+1. In the Cloudflare dashboard, go to the **Web assets** page.
+
+
+2. Go to the **Endpoints** tab.
+3. Choose the endpoint that you want to label.
+4. Select **Edit endpoint labels**.
+5. { props.labelName ? (
+ <>
+ Add the {props.labelName} label to the endpoint.
+
+ ) : (
+ <>
+ Add the label(s) that you want to use for the endpoint from the list of managed and user-defined labels.
+
+ )}
+6. Select **Save labels**.
+
+{/* prettier-ignore-end */}
From b1730a8fdb7161ec1d2aefb5641c9d7a9cda38cf Mon Sep 17 00:00:00 2001
From: Pedro Sousa <680496+pedrosousa@users.noreply.github.com>
Date: Wed, 5 Nov 2025 10:22:05 +0000
Subject: [PATCH 2/5] Move content to partial
---
.../endpoint-labels.mdx | 7 +------
.../api-shield/labels-add-old-nav.mdx | 19 +++++++++++++++++++
2 files changed, 20 insertions(+), 6 deletions(-)
create mode 100644 src/content/partials/api-shield/labels-add-old-nav.mdx
diff --git a/src/content/docs/api-shield/management-and-monitoring/endpoint-labels.mdx b/src/content/docs/api-shield/management-and-monitoring/endpoint-labels.mdx
index a073ca89d85720c..4ce56cf2ebdc18c 100644
--- a/src/content/docs/api-shield/management-and-monitoring/endpoint-labels.mdx
+++ b/src/content/docs/api-shield/management-and-monitoring/endpoint-labels.mdx
@@ -157,12 +157,7 @@ Alternatively, you can create a user-defined label via **Security** > **Web Asse
-1. Log in to the [Cloudflare dashboard](https://dash.cloudflare.com/), and select your account and domain.
-2. Go to **Security** > **API Shield** > **Endpoint Management**.
-3. Choose the endpoint that you want to label.
-4. Select **Edit labels**.
-5. Add the label(s) that you want to use for the endpoint from the list of managed and user-defined labels.
-6. Select **Save labels**.
+
diff --git a/src/content/partials/api-shield/labels-add-old-nav.mdx b/src/content/partials/api-shield/labels-add-old-nav.mdx
new file mode 100644
index 000000000000000..c321d53f172ff70
--- /dev/null
+++ b/src/content/partials/api-shield/labels-add-old-nav.mdx
@@ -0,0 +1,19 @@
+---
+params:
+ - labelName?
+---
+
+import { Markdown } from "~/components";
+
+{/* prettier-ignore-start */}
+
+1. Log in to the [Cloudflare dashboard](https://dash.cloudflare.com/), and select your account and domain.
+2. Go to **Security** > **API Shield**.
+3. In the **Endpoint Management** tab, choose the endpoint that you want to label.
+4. Select **Edit labels**.
+5. { props.labelName ?
+ :
+ "Add the label(s) that you want to use for the endpoint from the list of managed and user-defined labels." }
+6. Select **Save labels**.
+
+{/* prettier-ignore-end */}
From b3761f3ed286d34080567808bb31eb1790ad7ae0 Mon Sep 17 00:00:00 2001
From: Pedro Sousa <680496+pedrosousa@users.noreply.github.com>
Date: Wed, 5 Nov 2025 10:22:30 +0000
Subject: [PATCH 3/5] Small updates to instructions
---
src/content/partials/api-shield/labels-add.mdx | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/src/content/partials/api-shield/labels-add.mdx b/src/content/partials/api-shield/labels-add.mdx
index 27708c14ef5a08a..3bd5650ddeb413f 100644
--- a/src/content/partials/api-shield/labels-add.mdx
+++ b/src/content/partials/api-shield/labels-add.mdx
@@ -3,15 +3,14 @@ params:
- labelName?
---
-import { DashButton, Markdown } from "~/components";
+import { DashButton } from "~/components";
{/* prettier-ignore-start */}
1. In the Cloudflare dashboard, go to the **Web assets** page.
-2. Go to the **Endpoints** tab.
-3. Choose the endpoint that you want to label.
+2. In the **Endpoints** tab, choose the endpoint that you want to label.
4. Select **Edit endpoint labels**.
5. { props.labelName ? (
<>
From 925a35d9eeee9a0876489734c8b8812a040c0dd0 Mon Sep 17 00:00:00 2001
From: Pedro Sousa <680496+pedrosousa@users.noreply.github.com>
Date: Wed, 5 Nov 2025 10:22:57 +0000
Subject: [PATCH 4/5] Add instructions for old nav
---
.../firewall-for-ai/get-started.mdx | 64 ++++++++++++++++++-
1 file changed, 63 insertions(+), 1 deletion(-)
diff --git a/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx b/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
index af60ac377282483..8592a4cd2972bbf 100644
--- a/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
+++ b/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
@@ -55,6 +55,21 @@ Once you have [onboarded your domain](/fundamentals/manage-domains/add-site/) to
Save the relevant endpoint receiving LLM-related traffic to [Endpoint Management](/api-shield/management-and-monitoring/endpoint-management/) once it has been discovered, or add the endpoint manually.
+
+
+
+
+1. Log in to the [Cloudflare dashboard](https://dash.cloudflare.com/login), and select your account and domain.
+2. Go to **Security** > **API Shield**.
+3. Go to the **Discovery** tab.
+4. Find the endpoint receiving requests with LLM prompts in the list and select **Save** next to the endpoint.
+
+
+
+
+
+
+
1. In the Cloudflare dashboard, go to the **Web assets** page.
@@ -62,13 +77,36 @@ Save the relevant endpoint receiving LLM-related traffic to [Endpoint Management
2. Go to the **Discovery** tab.
3. Find the endpoint receiving requests with LLM prompts in the list and select **Save** next to the endpoint.
+
+
+
+
If you did not find the endpoint in the **Discovery** tab, you can add it manually:
+
+
+
+
+1. Go to the **Endpoint Management** tab.
+2. Select **Add endpoints** > **Manually add**.
+3. Choose the method from the dropdown menu and add the path and hostname for the endpoint.
+4. Select **Add endpoints**.
+
+
+
+
+
+
+
1. Go to the **Endpoints** tab.
2. Select **Add endpoints** > **Manually add**.
3. Choose the method from the dropdown menu and add the path and hostname for the endpoint.
4. Select **Add endpoints**.
+
+
+
+
In the context of this guide, consider an example endpoint with the following properties:
- Method: `POST`
@@ -81,17 +119,37 @@ You must [label endpoints](/api-shield/management-and-monitoring/endpoint-labels
Add the `cf-llm` label to the endpoint you added:
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Once you add a label to the endpoint, Cloudflare will start labeling incoming traffic for the endpoint with the label you selected.
## 4. (Optional) Generate API traffic
-You may need to issue some `POST` requests to the endpoint so that there is some labeled traffic to analyze in this step.
+You may need to issue some `POST` requests to the endpoint so that there is some labeled traffic to review in the following step.
For example, send a `POST` request to the API endpoint you previously added (`/v1/messages` in this example) in your zone with an LLM prompt requesting PII:
@@ -107,6 +165,8 @@ The PII category for this request would be `EMAIL_ADDRESS`.
Use [Security Analytics](/waf/analytics/security-analytics/) in the new application security dashboard to validate that the WAF is correctly labeling traffic for the endpoint.
+
+
1. In the Cloudflare dashboard, go to the **Analytics** page.
@@ -128,6 +188,8 @@ Use [Security Analytics](/waf/analytics/security-analytics/) in the new applicat
The displayed logs now refer to incoming requests where personally identifiable information (PII) was detected in an LLM prompt.
+
+
Alternatively, you can also create a custom rule with a _Log_ action (only available on Enterprise plans) to check for potentially harmful traffic related to LLM prompts. This rule will generate [security events](/waf/analytics/security-events/) that will allow you to validate your Firewall For AI configuration.
## 6. Mitigate harmful requests
From 2ce2ccea0fa2472131eb45277fc59c784b9da4c7 Mon Sep 17 00:00:00 2001
From: Pedro Sousa <680496+pedrosousa@users.noreply.github.com>
Date: Wed, 5 Nov 2025 14:12:50 +0000
Subject: [PATCH 5/5] Small update to the text
---
.../docs/waf/detections/firewall-for-ai/get-started.mdx | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx b/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
index 8592a4cd2972bbf..73439e694d2dbf9 100644
--- a/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
+++ b/src/content/docs/waf/detections/firewall-for-ai/get-started.mdx
@@ -151,7 +151,7 @@ Once you add a label to the endpoint, Cloudflare will start labeling incoming tr
You may need to issue some `POST` requests to the endpoint so that there is some labeled traffic to review in the following step.
-For example, send a `POST` request to the API endpoint you previously added (`/v1/messages` in this example) in your zone with an LLM prompt requesting PII:
+For example, the following command sends a `POST` request to the API endpoint you previously added (`/v1/messages` in this example) in your zone with an LLM prompt requesting PII:
```sh
curl "https:///v1/messages" \
@@ -163,7 +163,7 @@ The PII category for this request would be `EMAIL_ADDRESS`.
## 5. Review labeled traffic and detection behavior
-Use [Security Analytics](/waf/analytics/security-analytics/) in the new application security dashboard to validate that the WAF is correctly labeling traffic for the endpoint.
+Use [Security Analytics](/waf/analytics/security-analytics/) in the new application security dashboard to validate that Cloudflare is correctly labeling traffic for the endpoint.
@@ -190,7 +190,7 @@ Use [Security Analytics](/waf/analytics/security-analytics/) in the new applicat
-Alternatively, you can also create a custom rule with a _Log_ action (only available on Enterprise plans) to check for potentially harmful traffic related to LLM prompts. This rule will generate [security events](/waf/analytics/security-events/) that will allow you to validate your Firewall For AI configuration.
+Alternatively, you can also create a custom rule with a _Log_ action (only available on Enterprise plans) to check for potentially harmful traffic related to LLM prompts. This rule will generate [security events](/waf/analytics/security-events/) that will allow you to validate your Firewall for AI configuration.
## 6. Mitigate harmful requests