AI threat protection

---
title: AI threat protection
description: Learn how Now Assist helps defend against AI-specific threats including offensive content, prompt injection, and sensitive subject detection using AI Guardian.
locale: en-US
canonical_url: https://www.servicenow.com/docs/r/platform-security/naai-threat-protection.html
release: brazil
topic_type: concept
last_updated: "2026-09-10"
reading_time_minutes: 1
breadcrumb: [Agentic AI security and governance]
---

# AI threat protection

Learn how Now Assist helps defend against AI-specific threats including offensive content, prompt injection, and sensitive subject detection using AI Guardian.

AI Guardian monitors requests sent to large language models and their responses to protect you, your users, and your data. It detects offensive or harmful content, prompt injection attempts, and sensitive subjects, and can log or block detected content depending on your configuration.

## Configure guardrails

The following topics describe how to set up AI Guardian and configure the guardrails available for Now Assist skills and AI agents.

-   **[AI Guardian](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/now-assist-guardian.md)**

    Learn how AI Guardian monitors generative AI content at runtime, what categories of content it detects, and how logging and blocking work.

-   **[Setup a Guardrail Service Provider](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/configure-guardrail-model.md)**

    Manage the Guardrail service provider used by AI Guardian.

-   **[Activate offensiveness protection for generative AI](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/activate-offensiveness-protection-for-generative-ai.md)**

    Turn on offensiveness protection to log and optionally block offensive content in AI-generated text and conversations.

-   **[Configure prompt injection attack protection](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/configure-prompt-injection-attack-protection.md)**

    Activate or deactivate prompt injection attack protection for AI-generated text and conversations.

-   **[Configure sensitive topic filters](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/configure-sensitive-topic-filters.md)**

    Set up filters to redirect users to a different topic when certain subject material is detected in a Virtual Agent conversation.

-   **[Enable AI Guardian for AI agents](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/enable-aia-na-guardian.md)**

    Enable AI Guardian in AI agents to automatically identify and block offensive messages, helping protect your agentic workflows from harmful content.


## Monitor guardrail activity

The following topics describe how to review and export AI Guardian logs to evaluate guardrail effectiveness and support security review.

-   **[AI Guardian analytics](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/now-assist-guardian-analytics.md)**

    Monitor the performance of guardrails enabled through AI Guardian, including tracking how often offensive content and prompt injection attempts are detected.

-   **[Export AI Guardian logs](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/intelligent-experiences/export-now-assist-guardian-logs.md)**

    Export logs from AI Guardian to get insights into how often different guardrails are being detected and used.


**Parent Topic:**[Agentic AI security and governance](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/platform-security/now-assist-security.md)