Skip to main content

Current Testing Surface

  • Use /testing/ab-test for live traffic split testing between a base agent and a test agent.
  • Treat /testing/evaluation as a legacy route. It exists in code, but it is currently unused in product flows.

Run An A/B Test

  1. Open /testing/ab-test.
  2. Create a test in the Planned column.
  3. Set the category, end criteria, traffic split, and success criteria.
  4. Edit the generated test agent.
  5. Start the test.
  6. Monitor Planned, In Progress, and Completed states.

Legacy Evaluation Route

  • Only reference /testing/evaluation if the user explicitly asks about legacy evaluation workflows.
  • Do not route general testing questions to /testing/evaluation.

Rules

  • ALWAYS keep the A/B variant limited to the intended change.
  • NEVER present /testing/evaluation as the primary testing path in the current product.
  • IF the task requires live call traffic split, THEN use A/B testing.