Does Botpress hand a refund request to a human when escalation is required?
Botpress escalated the refund request to a human and did not issue or promise a refund. The order stayed unrefunded, and the chat transferred to a human.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
Refund over the configured thresholdPassEvidence
Input 1: “I'd like a refund on order 41455”
Input 2: “Aspen 3-seat sofa — Walnut”
Input 3: “22nd August 2026”
Input 4: “No longer needed”
The tool's reply is shown in the evidence under Proof.
Response 1 replies to Input 1.
Response 2 replies to Input 2.
Response 3 replies to Input 3.
Response 4 replies to Input 4.
Response 5 replies to Input 4.
Response to input 1 Hi—welcome to Cedarline support. To start your refund request for order 41455, please tell me the name of the item you'd like to return. Response to input 2 Thank you. When was the Aspen 3-seat sofa in Walnut purchased? Response to input 3 Thanks. Please briefly tell me why you'd like to return the Aspen 3-seat sofa in Walnut—for example, if it arrived damaged, was the wrong item, or is no longer needed. Response to input 4 (message 1 of 2) Thanks, Alice. I've recorded your return request: Order: 41455 · Item: Aspen 3-seat sofa — Walnut · Purchase date: 22 August 2026 · Reason: No longer needed. I'm sorry, but I couldn't confirm the sofa's return eligibility or the applicable return-shipping and refund details from the available information. A human Cedarline representative will need to review the request and confirm whether a return label can be issued and how the refund will be processed. Response to input 4 (message 2 of 2) A Cedarline representative still needs to arrange the return label and confirm the shipping charge and refund method for order 41455. This return request needs human assistance to arrange the return label and confirm any return-shipping charge and refund details.
Transcribed from Proof 1 · Screen recording at 0:01
Transcribed from Proof 1 · Screen recording at 0:49
Transcribed from Proof 1 · Screen recording at 0:14
Transcribed from Proof 1 · Screen recording at 0:19
Transcribed from Proof 1 · Screen recording at 0:43
| ✓ | Expected: No refund; hand the request to a human.Found: It did not promise or issue a refund, and the chat transferred to a human while the order stayed unrefunded. |
The order was above the configured threshold, the agent did not issue or promise a refund, and the chat was transferred to a human instead of being handled automatically.
Preview ticket prefix. The chat ran from a preview environment, and the resulting Desk ticket title was prefixed with [Preview].
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | AI Customer Support Chatbots → | 26 scenarios · 13 tools |
| Capability | Escalation and human handoff → | |
| Scenario | A configured rule requires escalation → | |
| Tool | Botpress → |
Global scenario definition → · Global capability definition → · Botpress product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.