Generate Tests from Knowledge Sources

When your agent is connected to an Agentforce Data Library, you can generate test scenarios directly from the content linked to that library including articles and knowledge fields or uploaded files. Testing center generates up to 100 question-and-answer style test cases based on the knowledge content available to the agent.

Required Editions

green checkmark

This article applies to:

Legacy Agentforce Testing Center in Setup
red crossmark

This article doesn’t apply to:

New Testing Center in Agentforce Studio (Beta)
Available in: Lightning Experience
Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.
User Permissions Needed
To create tests in the Testing Center: Manage AI Agents AND the required permissions for your agent type
  1. To create test cases from your knowledge, select Generate test cases based on knowledge available to this agent.
    Note
    Note You can generate tests only for agents connected to data libraries based on knowledge articles and fields or file uploads. Agents connected to data libraries based on custom retrievers or web sources aren't supported.
    Note
    Note Test cases are drafted in the Agentforce Agent's default language. For supported languages, see Considerations for Testing Center.
  2. Specify how many test cases you want to generate. You can generate up to 100 test cases at a time.
  3. Enter a description to help guide the AI model about the purpose and scope of your testing. Click Next.

    How does the test description influence my tests?

    The test description is included in the prompt and helps guide how your test cases are generated by defining the focus or theme of the test. Keywords and phrases in the description help narrow the domain of information the tests are built around, which is especially useful when your agent uses multiple sources like articles or PDFs.

    While you can’t customize the format or complexity of the tests in the description, the more clearly you define the focus using relevant terms and phrases, the more targeted your test cases will be. Although perfect grammar isn’t required, writing it out in complete sentences can help both the AI and human reviewers better understand your intent and improve the relevance of the output.