Using other Now Assist applications from Now Assist Center › Use › Now Assist Center › Enable AI experiences

Release: Australia · Updated: 2026-04-09 · Official documentation · View source

Use Now Assist Guardian features in Now Assist Center

Use Now Assist Guardian features in the Now Assist Center workspace to detect offensive content, prompt injection attacks, and sensitive topics in generative AI interactions.

Before you begin

The following applications must be installed before performing this task:

Now Assist Center

For more information, see Confirm installation of Now Assist Center.
Now Assist Admin console

For more information, see Install and configure essential Now Assist plugins using Now Assist Center.

Role required: sn_na_center.nac_admin

About this task

Follow these steps to use Now Assist Guardian capabilities from Now Assist Center.

Now Assist Guardian provides safety and governance controls for AI-generated content. It monitors AI interactions for potentially harmful, offensive, or policy-violating content.

In Now Assist Center, the integration of Now Assist Guardian includes multi-tabbing support for working with safety and governance controls without leaving the application context.

For more information on Now Assist Guardian, see .

Procedure

Navigate to All > Now Assist Center or Workspaces > Now Assist Center.
Select Admin (

Image omitted: icon-now-assist-center-nav-admin.png
Admin icon. \) in the side navigation bar.

The Admin tab opens showing Now Assist Admin options.

Select one of the options under Now Assist Guardian to configure.

Now Assist Guardian provides three guardrails. Each guardrail has a different scope.

Guardrail

Description

Prompt injection detection

This guardrail attempts to override LLM instructions or expose restricted information. It applies to all generative AI applications and features.

Select Prompt injection to open the Prompt injection tab.

For more information on how to configure this guardrail, see .

Offensiveness detection

This guardrail detects offensive or harmful content in AI inputs and outputs. It applies to specific Now Assist skills and workflows.

Select Offensiveness to open the Offensiveness tab.

For more information on how to configure this guardrail, see .

Sensitive topic filters

This guardrail filters subjects not suited for AI responses, such as workplace safety or employee compensation. It applies to Virtual Agent conversational skills only (available for HR Service Delivery and Customer Service Management).

Select Sensitive Filters to open the Filters tab.

For more information on how to configure this guardrail, see .

Parent Topic:Using other Now Assist applications and features from Now Assist Center