Save a library of questions you care about (opening hours, refund policy, pricing edge cases) and re-run them against your chatbot in one click. Each run gets a Pass, Fail, or Pending review verdict so you can catch problems before your customers do.
How to get there: Go to Setup → Chatbot in the top menu → click your chatbot → Advanced → Test Automation in the sidebar.
A test case is a saved question plus a description of what a correct answer looks like. When you run it, your chatbot answers as it would for a real visitor, and Boei compares the answer to what you expected.
Each case tracks:
You can run a single case with the Test button on its row, or run all active cases with Run selected. Each case runs through the same process your real chatbot uses, so everything works exactly as it would for a visitor.
If a case triggers a lead flow, you'll see a green indicator next to the response confirming it worked.
By default, Boei automatically compares the actual answer to your expected description and marks it as Pass or Fail with a one-line reason. This covers most cases without you having to review every response.
Turn it off with the switch in the toolbar if you'd rather review every run yourself. When the judge is off:
| Verdict | Meaning |
|---|---|
| Passed | The judge (or you) marked the answer correct |
| Failed | The judge (or you) marked the answer wrong |
| Pending review | Judge is off, waiting for you to Pass or Fail |
| Error | The chatbot couldn't answer (rate limit, low credits, or service issue) |
| Pending | Case hasn't been run yet |
The verdict banner sits at the top of each case card in color, so you can scan a long list for red rows fast.