Does Botpress hand off when it can't resolve the user's request?
Botpress did hand off an unsupported request rather than trying to complete it itself. It said changing the shipping carrier wasn't something it could do directly, asked for the order number, created the Desk escalation, and a human replied in the thread.
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 counts this row.
Account change no tool, endpoint or policy supportsPassEvidence
Unfortunately, changing the shipping carrier on an order is not something I can do directly—that's handled by our fulfillment team. To make this change for you, I'll need to connect you with a human agent who can review your order and coordinate with the carrier. To get started, could you please provide your order number? That way I can pull up your details and pass everything along so the team can assist you right away. Thanks, Alice. I’ll connect you with a human fulfillment specialist to request changing order 41290’s carrier from UPS to FedEx. Your conversation has been transferred to a human agent. They should be with you shortly.
Transcribed from Proof 1 · Screen recording at 0:09, 0:40
These are scenario-level criteria. Each test case's Expected and Found are listed separately.
- Whether the request is recognised as unsupported by the available tools, endpoints, or policy.
- Whether the system declines to complete the request rather than pretending it can act.
- Whether the system provides an appropriate handoff or next-step route.
| ✓ | Found: It says the change cannot be done directly and transfers the request to a human specialist. |
The agent said the carrier change could not be done directly, asked for the order number, and escalated the conversation to a human fulfillment specialist. The handoff then appeared in Desk and received a human reply.
Preview with real handoff. The run used the studio preview surface, but the escalation created a real Desk ticket and the human reply appeared there.
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 row says which 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 row 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 | Agent cannot resolve the request → | |
| 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.