Activate offensiveness protection for generative AI

---
title: Activate offensiveness protection for generative AI
description: Activate offensiveness detection to log or block offensive content generated by AI skills and workflows.
locale: en-US
canonical_url: https://www.servicenow.com/docs/r/australia/intelligent-experiences/activate-offensiveness-protection-for-generative-ai.html
release: australia
topic_type: task
last_updated: "2026-09-10"
reading_time_minutes: 2
keywords: [Generative AI, Gen AI, Now Assist, Admin, Guardian, offensiveness protection]
breadcrumb: [AI Guardian, AI Admin Hub Settings, Exploring AI Admin Hub, AI Admin Hub, Generative AI skills, Enable AI Experiences]
---

# Activate offensiveness protection for generative AI

Activate offensiveness detection to log or block offensive content generated by AI skills and workflows.

## Before you begin

Role required: sn\_nowassist\_admin.nsa\_admin

## About this task

Generative AI output is probabilistic, which means that the same input can produce different outputs. Some of the AI generated content may be offensive, which includes toxic, sexist, or other harmful language. AI Guardian enables you to detect offensive content in both inputs and outputs, and logs the event when it is detected. You can also cofigure it to block offensive material so that users see a standard error message instead of the generated response.

**Note:** Offensiveness detection applies only to specific AI skills and workflows.. For more information about the list of skills that support offensiveness detection, see [Now Assist Guardian](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/now-assist-guardian.md).

You can export logs for review. For more information, see [Export Now Assist Guardian logs](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/export-now-assist-guardian-logs.md).

## Procedure

1.  Navigate to **All** > **AI Admin Hub** > **Settings**.

2.  In the side panel, select the **Now Assist Guardian** > **Offensiveness** tab.

3.  Go to the **Available for you** tab to see which workflows you can choose from.

    Offensiveness guardrails that are already activated appear in the **Active** tab.

4.  Select **Activate** for the workflow that you want to enable offensiveness detection.

5.  Select your impact detection.

    -   Select **Log only** to record the events when offensive content is detected. The content is still shown to the user.
    -   Select **Block and log** to record the event and prevents the content from being shown to the user. The user sees a standard error message instead.
    \[Omitted image "na-guardian-activate-offensiveness.png"\] Alt text: Offensiveness guardrail for AI Guardian with option "log only" selected

6.  Select **Save**.


## Result

Offensiveness detection guardrail is enabled on your instance for the selected workflow. Events are logged when offensive content is detected or generated.

## What to do next

You can enable offensiveness detection for separately for each supported generative AI application and workflow. Repeat this task for each workflow on which you want offensiveness protection enabled.

To change the detection impact for an active workflow, select more options \(\[Omitted image "more-options-menu-item.png"\] Alt text: More options icon.\) icon in the list of active workflows and then select **Edit**.

To deactivate offensiveness protection for a workflow, select more options \(\[Omitted image "more-options-menu-item.png"\] Alt text: More options icon.\) icon in the list of active workflows and then select **Deactivate** .

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