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

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Evaluate agentic AI assets

# Evaluate agentic AI assets {#ariaid-title1}

* Release version: Australia
* 
* Updated March 18, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Agentic evaluations enable you to test agentic AI assets against defined datasets to verify quality before deployment. Run results score performance, identify issues, and provide opportunities for optimization.

## Get started {#agentic-evals__cf-app-landing-get-started}

|-|-|-|
| [ExploreExplore what agentic evaluations are and general guidelines for running them.](https://www.servicenow.com/docs/r5DAVTHJ43rFkz5ogx9Pkg "Automated evaluations test your agentic AI assets and help determine when they're ready for production. Learn more about how evaluations work, who they’re designed for, and the benefits they deliver.") | [EvaluateCreate evaluation runs, track their progress, and analyze and act on results.](https://www.servicenow.com/docs/rzpba1dBqwKoMJAn2Sa_iQ "Find guidance for every stage of the agentic evaluation lifecycle, from initial setup to reevaluation.") | [ReferenceLearn more about the roles, parser tool for custom metrics, and the results page.](https://www.servicenow.com/docs/Qpc~NWw4VRUpys0vZ6Hkog "Find technical reference material for roles, metrics, and output formats of agentic evaluations.") |
[ ]

{#agentic-evals__table_gyk_3rj_q3c} Automated evaluations for agentic AI are a structured quality assurance capability for agentic AI assets built in AI Agent Studio. Each evaluation run tests your agents against a defined dataset, applies LLM-powered judges to score key quality dimensions, and surfaces issues with recommended fixes. Use automated evaluations to
get objective, explainable evidence that your agentic AI is ready to deploy.

## Helpful resources {#agentic-evals__cf-app-landing-get-help}

Some ServiceNow resources that can provide you with helpful information are:

ServiceNow Community
:   [ServiceNow Community](https://community.servicenow.com/community)

Developer
:   [developer.servicenow.com](https://developer.servicenow.com/)


Impact
:   <http://impact.servicenow.com>


ServiceNow University
:   [ServiceNow University](https://learning.servicenow.com/now/lxp/home)

Best Practices
:   [Best Practices](https://mynow.servicenow.com/now/best-practices/home)

Partner
:   <https://www.servicenow.com/partners.html>


ServiceNow
:   <http://servicenow.com>


ServiceNow Store
:   <http://servicenow.com>

Support
:
    * <https://support.servicenow.com/now>
    * [Known Error Portal](https://support.servicenow.com/kb?id=known_error_portal)
    {#agentic-evals__ul_hzv_5pq_xcc}