Configure LLM to generate descriptions for conversational actions

task australia Updated Sep 10, 2026 1 min read configure-default-llm-for-conversational-actions.md
Raw file servicenow.com

Choose which LLM you want to use by default to generate descriptions for inputs, outputs, and skills for conversational actions.

Before you begin

Role required: admin

About this task

In the conversational actions settings, you can use generative AI to generate descriptions for skills, inputs, and outputs of a conversational action. You can select a default LLM to generate these descriptions out of any of the following preconfigured LLMs:

  • Anthropic Claude
  • Azure OpenAI
  • Google Gemini
  • Now LLM

Note: This configuration affects only the capability to generate the descriptions.

Procedure

  1. Select All.

  2. In the Filter search box, enter sys_one_extend_capability.list.

  3. In the OneExtend Capabilities list, search for the application Conversational subflows and actions.

    [Omitted image "csa-llm-generate-description.png"] Alt text: OneExtend Capabilities page shows entries for input - output description generator and skill description generator.

  4. Select the record for which you want to change the LLM:

    • Input output description generator
    • Skill description generator The OneExtend Definition Configs tab displays separate rows for each configured LLM. The following image shows one row each for Now LLM and Azure OpenAI.[Omitted image "csa-llm-list.png"] Alt text: Options to select the default LLM.
  5. In the Default column of your selected LLM, set the value as true.

    [Omitted image "CSA-change-default-llm.png"] Alt text: Selecting the default LLM for conversational subflows description generation skill.

    Once you select the default LLM, ensure that the Default field value for any other LLM is set to false.

  6. Select Update.

Parent Topic:Building actions

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