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

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Configure deployment and skill settings

# Configure deployment and skill settings {#ariaid-title1}

Release version: Brazil  
Updated September 10, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 minutes to read  
Configure where a skill appears in AI Admin Hub, review general information, set security controls, choose a provider, and add evaluation metrics.

## Before you begin

Role required: sn_skill_builder.admin

## About this task

The Deployment and skill settings tab contains five sections that you can configure in any order:

* Deployment settings: Choose where the admin can find and activate the skill in AI Admin Hub.
* General information: Review or edit the skill name and description.
* Security controls: Restrict which roles can run the skill.
* Providers: View the language model providers available for the skill.
* Evaluation metrics: Add metrics that measure the quality of skill responses.
{#configure-skill-settings__ul_sections_summary}

## Procedure

1. Navigate to AllAI Skill KitHome.
2. Select the skill that you want to configure.
3. Select the Deployment and skill settings tab.
4. Configure the Deployment settings section.  

   Under Now Assist features, fill in the fields.
   {#configure-skill-settings__table_qfd_3nh_lcc__entry__2}

   | Field | Description |
   |-|-|
   | Workflow | High-level category for the skill, such as Technology, Employee, Creator, or Platform. You can also select Other if none of the categories fit. The workflow that you choose is where the skill appears in the AI Admin Hub console. |
   | Product | Product that the skill operates within, such as ITSM, ITOM, HR Service Delivery, or AI Admin Hub. |
   | Feature | Feature that the skill is used in, such as Agent Chat, Knowledge, or Virtual Agent. You can also define a custom feature. |
   | Name | Name of the feature. |
   | Description | Description of the feature. |
   [Table 1. Deployment settings form]

   {#configure-skill-settings__table_qfd_3nh_lcc}

   Under Select where you'd like to let the admin activate the skill, select one or more activation points.
   * Now Assist panel
   * UI Action
   * Flow action
   * Now Assist context menu
   * Virtual assistants

     For more information about Now Assist in Virtual Agent, see [Configure assistants overview](https://www.servicenow.com/docs/access?context=configure-now-assist-va&version=brazil&pubname=brazil-conversational-interfaces&ft:locale=en-US).
   * UI Builder
   {#configure-skill-settings__ul_jrq_nzw_gdc}
5. Review the General information section.  
   This section shows the information that you added when you created the skill. You can edit the skill name and description here.
6. Configure the Security controls section to restrict which roles can run the skill.  
   For the procedure, see [Configure security controls for a skill](https://www.servicenow.com/docs/BqlAqPG0ojp8ADB~Eb3V_g "Define an access control list (ACL) and role restrictions for every skill. The ACL limits which user roles can access and run the skill, and role restrictions limit the roles that the skill runs with.").
7. Review the Providers section.  
   The Providers section lists the language model providers available for the skill. Each provider is tagged as Default or Not supported where
   applicable.  
   Important:  
   The runtime model depends on the configuration in AI Admin Hub and may differ from what's shown in the Providers section.
8. **Optional:** Add one or more Evaluation metrics to measure the quality of skill responses.  
   Evaluation metrics attached in this section apply to every prompt test that you run on the skill.  
   Important:  
   LLM-judged evaluation metrics consume additional Now Assist assists during prompt testing. Metric execution is billed as a custom call at one assist per 1,000 output tokens, so metrics that produce longer output consume more assists.

   Script-based metrics (metrics with a script instead of a judge prompt) don't consume assists.

   For details about Now Assist consumption during prompt testing, see [Test a prompt](https://www.servicenow.com/docs/lbl0exKhp6U2ZkGlLL33UA "After you create a prompt for your custom skill, test it before you finalize it to verify that it returns the expected results.").
   1. In the Evaluation metrics section, select the add icon ![]().
   2. From the list of available metrics, select the metric that you want to add.  
      Metrics are grouped by category. Each metric shows the language model provider that runs the metric, such as Amazon Bedrock, Now LLM Generic, or
      Multiple LLMs. Metrics that run as scripts don't display a provider tag.

      For descriptions of the available metrics, see [Evaluate a prompt](https://www.servicenow.com/docs/dmWxQaJDYd4ukGuGzxtfRA "Use the AI Skill Kit evaluation tools to measure how your skill prompts perform against a dataset, using automated metrics and human feedback.").
   3. Review the metric details.  
      {#configure-skill-settings__table_metric_tabs__entry__2}

      | Tab | Description |
      |-|-|
      | About | Description of the metric, how it works, when to use it, and its output format. |
      | Judge Prompt / Script | Prompt that a language model uses to judge the response, or script that evaluates the response, depending on how the metric is implemented. |
      [Table 2. Metric detail tabs]

      {#configure-skill-settings__table_metric_tabs}
   4. Select Add.
   {#configure-skill-settings__substeps_add_metric}
9. Select Save.

## What to do next

After you configure the deployment and skill settings, you can publish your skill. To learn more about publishing skills, see [Finalize and publish a skill](https://www.servicenow.com/docs/6QCdI481r211gzsodCxv5w "Finalize at least one prompt and publish your custom skill so that a Otto admin can activate it.").
**Related tasks**   

* [Configure a skill prompt](https://www.servicenow.com/docs/rNMRoXbSgi0MFboenCkUMA "Configure a skill prompt to set its large language model (LLM), the randomness of its responses, and its token limits.")
* [Configure security controls for a skill](https://www.servicenow.com/docs/BqlAqPG0ojp8ADB~Eb3V_g "Define an access control list (ACL) and role restrictions for every skill. The ACL limits which user roles can access and run the skill, and role restrictions limit the roles that the skill runs with.")

*[\>]: and then