---
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

# Evaluating 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

Find guidance for every stage of the agentic evaluation lifecycle, from initial setup to reevaluation.

## Overview of agentic evaluations {#evaluating-aia__cf-using-parent-workflow}

To evaluate your agentic AI at scale, follow the workflow described below:

1. [Create your first automated evaluation run.](https://www.servicenow.com/docs/3X0poPR_YJgX4XI5UXgpQA "Learn what you need to run your first agentic evaluation.")

   Get acquainted with the agentic evaluations homepage and the guided setup for an automated evaluation.
2. [Track and monitor progress.](https://www.servicenow.com/docs/qPEllXLPgdd43zZRS3~2Ww "Monitor the status of an active evaluation run to catch errors early and confirm when results are ready to review.")

   In-progress automated evaluations can provide important information about agentic AI performance. See any initial problems before all the results come through.
3. [Review the result outputs.](https://www.servicenow.com/docs/M0xBhZgkYkLK50Q8JAoitw "Assess your agent's overall performance after a run completes, including per-metric scores and issue counts. Use the results as your starting point for diagnosing quality issues and opportunities for improvement before deployment.")
   1. See LLM-judged scores.
   2. [Identify consistent issues.](https://www.servicenow.com/docs/v8S40zQcbDB9w9Q6P3LNyQ "Identify and prioritize specific quality failures detected during an evaluation run, organized by severity. Use issue severity and metric relevance to decide which failures to address before deployment.")
   3. [Trace issues back to their source.](https://www.servicenow.com/docs/OWYmUZdd6VqjzhgbKSln6w "Investigate the full record of an agentic interaction to diagnose the root cause of a quality failure. Trace each step the agent took, including tool calls and outputs, to pinpoint where things went wrong.")
   4. [Apply optimizations.](https://www.servicenow.com/docs/l0Z6r6WbJYy2qlrWMliArQ "Review and accept system-generated recommendations to improve agent quality based on detected issues. Apply optimizations before triggering a re-evaluation to confirm that changes resolved the failures.")
4. [Create automated evaluation runs for other agentic workflows or AI agents.](https://www.servicenow.com/docs/FVbxxoeAAPQLHkG3G7BqyA "Evaluate agentic AI assets against datasets to monitor performance and compare benchmarks.")
5. [Create custom metrics to evaluate against your specific business needs.](https://www.servicenow.com/docs/34tUTtgIKmlFXDcIsHkXXA "Create a custom metric for evaluating AI agents and agentic workflows to test the outputs against expected responses.")
{#evaluating-aia__cf-using-parent-steps-ol}

## Additional information {#evaluating-aia__cf-using-more-info}

* [Frequently asked questions about agentic evaluations](https://www.servicenow.com/docs/B3A~MD~kBdmRNpVOadaX5Q "Find answers to common questions about setting up and running evaluations.")
* [Troubleshoot agentic evaluations](https://www.servicenow.com/docs/5YQwb0Jyb2g0S9vRkdFoHQ "Find solutions to common evaluation errors, including run failures, data ingestion issues, and unexpected results.")