Does Intercom Fin hand off requests it cannot resolve?
Intercom Fin handled the unsupported account email change by declining it and directing the customer to support. It gave email and phone contact details, told the customer what to include, and ended by asking whether that was what they were looking for.
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.
Account change no tool, endpoint or policy supportsPassEvidence
“Change my account's email address”
Response to input 1 (message 1 of 2) To change the email address on your account, you'll need to contact our support team directly.
You can do that by:
- Emailing support@cedarline.com
- Calling 1-800-CEDAR-01 (Mon–Sat, 9am–7pm MT)
Email replies usually come within about 24 hours. When you reach out, include your current email and the new one you want to use so the request can be reviewed.
Response to input 1 (message 2 of 2) Is that what you were looking for?
Show the reply as returned (Markdown)
Response to input 1 (message 1 of 2) To change the email address on your account, you'll need to contact our support team directly. You can do that by: - Emailing support@cedarline.com - Calling 1-800-CEDAR-01 (Mon–Sat, 9am–7pm MT) Email replies usually come within about 24 hours. When you reach out, include your current email and the new one you want to use so the request can be reviewed. Response to input 1 (message 2 of 2) Is that what you were looking for?
Transcribed from Proof 1 · Screenshot
| ✓ | Expected: Cannot do the change and gives the customer a human route.Found: It says the support team must handle the change and gives email and phone contact details, hours, reply timing, and what to include. |
The request had no supported tool, endpoint, or policy, so Fin needed to decline the change and route the customer elsewhere. It did both by pointing to support and giving contact details plus request instructions.
Same reply. Fin's closing question was in the same reply, not a separate turn.
Concrete route. The route included an email address, a phone number with hours, reply timing, and what to include.
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 · 14 tools |
| Capability | Escalation and human handoff → | |
| Scenario | Agent cannot resolve the request → | |
| Tool | Intercom Fin → |
Global scenario definition → · Global capability definition → · Intercom Fin 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.