Run repeatable conversation suites and release gates before deployment.
Simulation suites test agents across repeatable scenarios before deployment. Use them when a workflow needs more coverage than a single manual preview can provide.
Simulation summarizes suite volume, recent runs, pass rate, failures, spend, and release-gate status.
Create scenarios for the expected conversation, missing or malformed information, caller interruptions, tool failures, transfers, voicemail, silence, and policy boundaries. Select the agent version and test methods the suite should exercise.
Use the suite pass rate and failed-scenario count to find regressions. Open a failed run, inspect the transcript and evaluation result, correct the prompt, flow, action, knowledge, or speech settings, and run the suite again.Mark critical suites as release gates so a failing result is visible before deployment. A passing suite is evidence for the tested scenarios, not a guarantee that every production call will succeed.
Keep suites small enough to diagnose quickly, and separate critical release gates from broader exploratory coverage.
