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
Prompt library

Test agent responses

Create, update, and delete test cases, and trigger test runs to validate Agent behavior before changes go live.

PromptWhat it does
”Create a test case for ‘I want to cancel my subscription’ on the web channel.”Creates a new test case with the specified message and channel.
”Update my expected outcomes to check that the Agent offers a retention discount before processing cancellation.”Refines evaluation criteria on an existing test case.
”Delete test cases that are no longer relevant after the refund policy change.”Removes outdated test cases.
”Run tests for all my billing-related test cases.”Triggers test execution and returns pass/fail results.
”Rerun my last test run.”Re-executes the most recent test run.
”Based on my production conversations, create test cases for the top 5 unresolved topics.”Analyzes conversation data and creates targeted test cases.
Was this page helpful?
Previous

Deep-dive analysis

Next
Built with