---
sourceDocument: Australia Platform security
sourceDocumentLink: https://www.servicenow.com/docs/r/platform-security

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Platform security

ft:clusterId :

    - psec

bundleId :

    - psec

workflow :

    - Platform


---

# Test and validate

# Test and validate {#ariaid-title1}

* Release version: Australia
* 
* Updated March 26, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Test and validate

This guide helps ServiceNow customers ensure their AI agents are ready for production deployment by validating agent execution, access controls, automated evaluations, and security monitoring through Guardian logs.
Testing confirms that the agent performs its intended functions correctly and that security configurations operate as expected.
Show full answer Show less  

## Test agent execution

Use the AI Agent Studio testing playground to manually run test executions with sample utterances. This lets you verify the agent's ability to complete tasks, utilize the correct tools, and handle edge cases and failures properly. Separate instructions exist for testing AI agent executions and agentic workflow executions.

## Test access controls

Validate access control lists (ACLs) by running access tests as different users. Confirm that only authorized users can invoke the agent, and unauthorized users are blocked. If access test results are unexpected, review and adjust your ACL configurations, considering interactions across agent, workflow, and tool layers.

## Run automated evaluations

After manual testing, run automated evaluations against datasets of expected inputs and outputs to obtain consistent, repeatable performance metrics. Ensure the user running these evaluations has the necessary ACL permissions; otherwise, errors will report access failures rather than execution failures.

## Review Guardian logs

Export and analyze AI Guardian logs generated during testing to identify any content flagged by security filters. This helps confirm that blocking configurations are appropriate for production. Adjust filters if unexpected detections occur, such as overly broad sensitive topic filters or test utterances triggering offensiveness detection.

## Go-live validation gate

Do not move to production deployment until all the following criteria are met:

* Agent execution tests successfully pass defined use case scenarios.
* Access control tests restrict invocation to intended users only.
* Automated evaluations meet success thresholds.
* Guardian logs confirm security configurations are suitable for production.

## Next steps

Once all validation criteria are satisfied, proceed with the go-live process and begin monitoring the agent in production.  
Test your agent's execution and access controls, run automated evaluations, and
review Guardian logs before approving the agent for production deployment.

Testing validates both that your agent performs its intended task correctly and that your
security configuration works as designed. Both dimensions must pass before you deploy to
production.

## Test agent execution {#naai-tutorial-test-validate__section_functional}

Use the testing playground in AI Agent Studio to run manual test
executions against your agent using sample utterances. Verify that the agent completes
its intended task, uses the correct tools, and handles edge cases and failure scenarios
appropriately.

* To test an AI agent execution, see [Manually test the execution of an AI agent](https://www.servicenow.com/docs/access?context=test-ai-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).
* To test an agentic workflow execution, see [Manually test the execution of an agentic workflow](https://www.servicenow.com/docs/access?context=test-aia-use-case&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

## Test access controls {#naai-tutorial-test-validate__section_access}

Verify that your ACL configuration works correctly by running access tests as different
users. Confirm that users who should have access can invoke the agent, and users who
should not have access cannot.

* To test user access to an AI agent, see [Test user access to an AI agent](https://www.servicenow.com/docs/access?context=test-aia-access&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).
* To test user access to an agentic workflow, see [Test user access to an agentic workflow](https://www.servicenow.com/docs/access?context=test-aw-access&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

If access test results are unexpected, review your ACL configuration. See [Implement access control in AI agents](https://www.servicenow.com/docs/access?context=aia-security-implementation&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) for details on how ACLs interact
across the agent, workflow, and tool layers.

## Run automated evaluations {#naai-tutorial-test-validate__section_automated}

Automated evaluations test your agent against a dataset of expected inputs and outputs, providing consistent, repeatable quality measurements. Run evaluations after manual testing is complete to establish a performance baseline
before go-live. For details on this process, see [Execute an agentic evaluation run](https://www.servicenow.com/docs/access?context=execute-aia-eval&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).  
Important:  
The user running an automated evaluation must pass the ACLs of the agent and all agents in the agentic workflow. If the user does not have the required roles, the evaluation will report an access failure rather than an agent execution failure.

## Review Guardian logs from testing {#naai-tutorial-test-validate__section_guardian_review}

Export and review AI Guardian logs from your test runs before
going live. The logs show you what content Guardian detected during testing, which helps
you decide whether your current blocking configuration is appropriate for production use.
See .

If you see unexpected detections in the logs, adjust your Guardian configuration before
proceeding. Common causes include overly broad sensitive topic filters or test utterances
that trigger offensiveness detection.

## Go-live validation gate {#naai-tutorial-test-validate__section_gate}

Do not proceed to [Go live and monitor](https://www.servicenow.com/docs/LtrHVbAzQ4ggq3Kc7GTlsQ "Deploy your agent to production, activate analytics and monitoring, and establish the ongoing review cadence that keeps your agent performing securely over time.") until all of the following are true:

* Agent execution tests pass for your defined use case scenarios.
* Access control tests confirm that only intended users can invoke the agent.
* Automated evaluations meet your defined success criteria threshold.
* Guardian logs from testing have been reviewed and configuration is confirmed appropriate for production.

## Next step {#naai-tutorial-test-validate__section_next}

When all validation gate criteria are met, proceed to [Go live and monitor](https://www.servicenow.com/docs/LtrHVbAzQ4ggq3Kc7GTlsQ "Deploy your agent to production, activate analytics and monitoring, and establish the ongoing review cadence that keeps your agent performing securely over time.").