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

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Test a prompt

# Test a prompt {#ariaid-title1}

Release version: Australia  
Updated September 23, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
After you create a prompt for your custom skill, test it before you finalize it to verify that it returns the expected results.

## Before you begin

Role required: sn_skill_builder.admin

## Procedure

1. Navigate to AllAI Skill KitHome.
2. Select the skill that you created the prompt for.
3. In the Test prompt section, select Run tests.
4. Select a test record, such as an incident.
5. Select Run test.  
   Important:  
   Testing a skill consumes at least one Now Assist assist for the base prompt call.

   If the skill has LLM-judged evaluation metrics attached on the Deployment and skill settings tab, each metric execution consumes additional assists. Metric execution is billed as a custom
   call at one assist per 1,000 output tokens. Script-based metrics (metrics with a script instead of a judge prompt) don't consume assists.

   For information about adding evaluation metrics, see [Configure deployment and skill settings](https://www.servicenow.com/docs/NnJpkW5tQPC6wXy6Cur5DQ "Configure where a skill appears in AI Admin Hub, review general information, set security controls, choose a provider, and add evaluation metrics.").  
   {#test-prompt-template__table_bw4_twh_lcc__entry__2}

   | Tab | Description |
   |-|-|
   | Response | Result that the large language model (LLM) returns for the prompt. |
   | Grounded prompt | Prompt with the data from your skill inputs and tools filled in. Use this view to verify that your skill inputs and tools return the correct data. |
   [Table 1. Prompt results]

   {#test-prompt-template__table_bw4_twh_lcc}
6. **Optional:** If the skill is deployed as a flow, turn off the com.glide.oneapi.fdih.async.quick.mode system property, and then turn on flow reporting.  
   This property controls whether flow execution details are generated when running flows, subflows, and actions from a custom skill. You can use flow execution details to test and troubleshoot your flow, subflow, or action. For more information about the system property, see [Workflow Studio flow system properties](https://www.servicenow.com/docs/access?context=flow-designer-system-properties&version=australia&pubname=australia-build-workflows&ft:locale=en-US).
7. **Optional:** Refine the prompt and repeat testing as needed.
8. **Optional:** Select the run test history icon ![]() to see the results from your previous run tests.

## What to do next

After you test your prompt, finalize the prompt and publish the skill. To learn more about publishing a skill, see [Finalize and publish a skill](https://www.servicenow.com/docs/BJGUHiV2QSMt_6N4aFfrcQ "Finalize at least one prompt and publish your custom skill so that a Otto admin can activate it.").

If you have not configured the deployment settings for your skill, see [Configure deployment and skill settings](https://www.servicenow.com/docs/NnJpkW5tQPC6wXy6Cur5DQ "Configure where a skill appears in AI Admin Hub, review general information, set security controls, choose a provider, and add evaluation metrics.").
**Related tasks**   

* [Create a skill](https://www.servicenow.com/docs/LKwxb28v59W_28ULmgLTkg "Create a custom skill for Otto. Custom skills extend the generative AI capabilities of Otto to fit your own use cases.")
* [Create a prompt](https://www.servicenow.com/docs/9Sb9G2tHYaTxJEgUaEZX0g "After you create a custom skill, create a prompt. The prompt defines the instructions that the skill sends to the LLM and the skill inputs that it uses.")
* [Use prompt assistance](https://www.servicenow.com/docs/BKzZKeozPhhC_WEW8cl03A "Use prompt assistance to start your prompt from an example in the prompt library or from a prompt that ServiceNow Otto generates.")
* [Evaluate a prompt](https://www.servicenow.com/docs/seUSWWx6xYOAQ3Duff4jig "Use the AI Skill Kit evaluation tools to measure how your skill prompts perform against a dataset, using automated metrics and human feedback.")
* [Finalize and publish a skill](https://www.servicenow.com/docs/BJGUHiV2QSMt_6N4aFfrcQ "Finalize at least one prompt and publish your custom skill so that a Otto admin can activate it.")
* [Activate a skill](https://www.servicenow.com/docs/6tjeJEpB9pCt6ypF5ez6Mg "After you create and publish a custom skill, you must activate it in AI Admin Hub. Activating the skill enables you to trigger the skill within the UI.")
* [Call a custom skill from a script](https://www.servicenow.com/docs/RSN7scujo7MlEPTcQuVkdA "Call a custom skill from a UI action script so that you can run the skill and use its output in your instance logic.")

*[\>]: and then