---
title: New DLP topic based detection entries for AI prompt protection
description: Analyze and secure user prompts to popular generative AI services with new, DLP topic classifications.
image: https://developers.cloudflare.com/changelog-preview.png
---

[Skip to content](#%5Ftop) 

# Changelog

New updates and improvements at Cloudflare.

[ Subscribe to RSS ](https://developers.cloudflare.com/changelog/rss/index.xml) [ View RSS feeds ](https://developers.cloudflare.com/fundamentals/new-features/available-rss-feeds/) 

![hero image](https://developers.cloudflare.com/_astro/hero.CVYJHPAd_26AMqX.svg) 

[ ← Back to all posts ](https://developers.cloudflare.com/changelog/) 

## New DLP topic based detection entries for AI prompt protection

Aug 25, 2025 

[ Data Loss Prevention ](https://developers.cloudflare.com/cloudflare-one/data-loss-prevention/) 

You now have access to a comprehensive suite of capabilities to secure your organization's use of generative AI. AI prompt protection introduces four key features that work together to provide deep visibility and granular control.

1. **Prompt Detection for AI Applications**

DLP can now natively detect and inspect user prompts submitted to popular AI applications, including **Google Gemini**, **ChatGPT**, **Claude**, and **Perplexity**.

1. **Prompt Analysis and Topic Classification**

Our DLP engine performs deep analysis on each prompt, applying [topic classification](https://developers.cloudflare.com/cloudflare-one/data-loss-prevention/detection-entries/#ai-prompt-topics). These topics are grouped into two evaluation categories:

* **Content:** PII, Source Code, Credentials and Secrets, Financial Information, and Customer Data.
* **Intent:** Jailbreak attempts, requests for malicious code, or attempts to extract PII.

To help you apply these topics quickly, we have also released five new predefined profiles (for example, AI Prompt: AI Security, AI Prompt: PII) that bundle these new topics.

![DLP](https://developers.cloudflare.com/_astro/ai-prompt-detection-entry.4QmdkAuv_Z14HtSJ.webp) 
1. **Granular Guardrails**  
You can now build guardrails using Gateway HTTP policies with [application granular controls](https://developers.cloudflare.com/cloudflare-one/traffic-policies/http-policies/#granular-controls). Apply a DLP profile containing an [AI prompt topic detection](https://developers.cloudflare.com/cloudflare-one/data-loss-prevention/detection-entries/#ai-prompt-topics) to individual AI applications (for example, `ChatGPT`) and specific user actions (for example, `SendPrompt`) to block sensitive prompts.  
![DLP](https://developers.cloudflare.com/_astro/ai-prompt-policy.CF3H2rbK_2muoEC.webp)
2. **Full Prompt Logging**  
To aid in incident investigation, an optional setting in your Gateway policy allows you to [capture prompt logs](https://developers.cloudflare.com/cloudflare-one/data-loss-prevention/dlp-policies/logging-options/#log-generative-ai-prompt-content) to store the full interaction of prompts that trigger a policy match. To make investigations easier, logs can be filtered by `conversation_id`, allowing you to reconstruct the full context of an interaction that led to a policy violation.  
![DLP](https://developers.cloudflare.com/_astro/ai-prompt-log.ywQDc5qN_2v6nax.webp)

AI prompt protection is now available in open beta. To learn more about it, read the [blog ↗](https://blog.cloudflare.com/ai-prompt-protection/#closing-the-loop-logging) or refer to [AI prompt topics](https://developers.cloudflare.com/cloudflare-one/data-loss-prevention/detection-entries/#ai-prompt-topics).