---
sourceDocument: Yokohama Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/yokohama/intelligent-experiences

 Release :

    - yokohama

ft:locale :

    - en-US

ft:publication_title :

    - Yokohama Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Export AI Guardian logs

# Export AI Guardian logs {#ariaid-title1}

Release version: Yokohama  
Updated July 31, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Export logs from AI Guardian to get insights into how often different guardrails are being detected and used.

## Before you begin

Role required: sn_generative_ai.nsa_admin

## About this task

AI Guardian logs all three types of guardrails available. Reviewing the logs can help you determine how often offensive content is generated, prompt injection attack attempts occur, or sensitive
topics are detected.

See [Now Assist Guardian](https://servicenow-prod.fluidtopics.net/H0bVbM_NdghPjzLAF~OnJg#now-assist-guardian "AI Guardian is built on the ServiceNow Small Language Model (SLM) and monitors generative AI interactions to detect offensive content, prompt injection attacks, and sensitive topics.") for more information.

## Procedure

1. Navigate to AllNow Assist AdminSettings.
2. Select the more options menu icon (![More options icon.]()) and select Export.
   1. For the offensiveness guardrail, go to Now Assist GuardianOffensiveness.  
      Use the list in the Active tab to select which workflow you want to export logs for.
   2. For the prompt injection guardrail, go to Now Assist GuardianPrompt Injection.
   3. For the sensitive topics, go to Now Assist GuardianFilters.

## Result

The log is exported as a .csv file to your computer.

## What to do next

If you do not see any log data, then it is most likely that the guardrail has not been triggered yet. If you believe you should be seeing data but aren't, reach out to Now Support.

*[\>]: and then