Configure a skill prompt

task brazil Updated Sep 10, 2026 1 min read configure-skill-prompt.md
Raw file servicenow.com

Configure a skill prompt to set its large language model (LLM), the randomness of its responses, and its token limits.

Before you begin

Role required: sn_skill_builder.admin

Procedure

  1. Navigate to All > AI Skill Kit > Home.

  2. Select the skill that you want to configure.

  3. Select Configurations.

    [Omitted image "nask-configurations.png"] Alt text: Configuration panel for the AI Skill Kit prompt.

  4. On the form, fill in the fields.

Field

Description

Model

Large language model (LLM) to use for the prompt.

Temperature

Randomness and creativity of the output. A higher value increases randomness. The value must be from 0 through 1.

Maximum response tokens

Maximum number of tokens that the model can return. If you’re using Now LLM Service, the maximum is 1,000.

Maximum request tokens

Maximum number of tokens allowed in a request.

Structured output

Option to return prompt responses in a consistent JSON format. Note: Only Google Gemini and Azure OpenAI support structured output. This option is not available when using Now LLM Service.

5. Add **Usage conditions** to determine when to use the prompt.

What to do next

After you configure your skill prompt, you can test it. To learn more about testing skills, see Test a prompt.

To learn more about configuring the skill, including models and tokens, see AI Skill Kit FAQs on the ServiceNow Community.

Parent Topic:Configuring AI Skill Kit

Related topics

Configure deployment and skill settings

Configure security controls for a skill

Search documentation
Search document titles and file paths on the brazil branch