---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Turn on the AICT Security Analyzer agent

# Turn on the AICT Security Analyzer agent {#ariaid-title1}

Release version: Brazil  
Updated October 28, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Turn on the AICT Security Analyzer agent to get additional analysis of AI asset security events. The agent classifies events by severity, adds them to Your top recommendations, and creates relevant security tasks.

## Before you begin

Role required: AI steward \[sn_ai_governance_ai_steward\]

## About this task

The AICT Security Analyzer agent is turned off by default, so that no AI usage is consumed until you choose to turn it on. When the agent is turned on, it analyzes security events using historical trends and intents. For more information about the agent, see [AICT security analyzer AI agent](https://www.servicenow.com/docs/I6VfeSsDwTtCNpYGbDmt_g#plat-ai-aict-security-analyzer-agent-ai-agent "This AI agent generates context for a detected AI security event by aggregating asset, prompt, cross-threat, and correlation data. It then computes a confidence score from detection strength, event risk, and authorization signals.").  
Note:  
When you turn on the agent, any Post-runtime settings that are enabled increase monitoring for threats and may increase token consumption.

## Procedure

1. In AI Control Tower, navigate to SettingsRules and templatesSecurity.
2. Select the Security insights tab.  
   The AICT Security Analyzer section shows the current status of the agent.
3. Select the arrow for Open in AI Agent Studio.
4. In AI Agent Studio, turn on the AICT Security Analyzer agent.  
   For more information, see [AI Agent Studio](https://www.servicenow.com/docs/4jkBhFj66oqonmoGg5aXdg "Build and deploy autonomous AI agents that automate complex workflows. AI Agent Studio is your command center for creating, configuring, and deploying autonomous AI agents that learn your business processes and act on them. Configure agents that learn your processes and handle routine work at scale—while you stay in control and focus on strategic priorities.").
{#gov-sec-configure-security-analyzer-agent__steps_sa_agent_1}

## Result

The AICT Security Analyzer agent starts analyzing security events for the settings you have enabled. To confirm, return to the Security insights tab. The status of the agent shows
Enabled.

## AICT Security Analyzer agent and Post-runtime settings {#ariaid-title2}

Post-runtime probabilistic metrics require that the AICT Security Analyzer agent is turned on. Both the AI agent and probabilistic metrics are turned off by default, and the sampling rate for the metrics is set to 1%. Turn them
on to get additional monitoring and analysis of your AI systems.

### Metrics turned off by default

The following metrics are turned off by default so that no AI usage is consumed until you choose to turn them on. For more information about configuring these metrics, see [Configure post-runtime security metrics](https://www.servicenow.com/docs/mUuxKq6x8npD4wo7cTcCJg "Customize security and content moderation policies, sampling rate, skill call usage limit, LLMs to use, and other settings for the Top AI asset security events metric and others.").  
Warning:  
AI judge model classifications are probabilistic in nature and may be incomplete or incorrect. They don't constitute professional advice and shouldn't be relied on as the sole basis for assessing risk.

* Agent goal deviation
* Correctness detection
* Data integrity incident detection
* Excessive agency
* Improper input and output handling
* Prompt injection
* Sensitive data disclosure
* System prompt leakage
{#gov-sec-aict-security-analyzer-agent-using__ul_hgd_pzh_blc}

*[\>]: and then