For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Login
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
  • Introduction
    • Overview
    • Getting started
    • Authentication
    • Data privacy
    • Built-in prompts
    • FAQ
    • Troubleshooting
  • Tools
    • Overview
    • get_ada_configuration
    • get_ada_metric
    • get_available_filters
    • get_conversations
    • get_conversation
    • search_knowledge
    • search_coaching
    • get_improvement_guide
    • list_entities
    • propose_change
    • get_test_cases
    • get_test_runs
    • get_test_run_quota
    • send_feedback
  • Prompt library
    • Overview
    • Improvement recommendations
    • Quick health checks
    • Create visualizations
    • Diagnose performance issues
    • Identify optimization opportunities
    • Review configuration
    • Search knowledge and coaching
    • Test agent responses
    • Deep-dive analysis
Login
LogoLogo
On this page
  • Example prompts
  • Parameters
  • Response
Tools

get_test_cases

Was this page helpful?
Previous

get_test_runs

Next
Built with

Retrieves test cases configured for an AI Agent. Supports listing all test cases, filtering by name, retrieving full details for a single test case, and grouping by channel.

Example prompts

  • “Show me all test cases on our Agent.”
  • “Find test cases whose name mentions ‘refund’.”
  • “Group my test cases by channel so I can see Voice vs. Chat coverage.”

Parameters

ParameterTypeDescription
test_case_idstringOptional. Return full details for a single test case.
name_filterstringOptional. Case-insensitive substring match against test case names.
group_bystringOptional. Set to channel to group the response by channel.

Response

When listing:

  • Test case ID and name.
  • Channel.
  • Message.
  • Evaluation criteria.
  • Last-updated timestamp.

When requesting a single test case by ID, the full test case definition is returned including any expected outcomes and metadata.