Does Intercom Fin choose the right source or action for a request?
Intercom Fin passed this order-status request. It answered from the order system, and the returned shipped status, carrier, tracking number, and delivery address matched what it told the customer.
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.
Order status must come from the order systemPassEvidence
“where is order 41982?”
Order 41982 has already shipped. Carrier: UPS. Tracking number: 1Z999AA10123456784. Shipped: Oct 26, 2026. Estimated delivery: Oct 29, 2026. Delivery address: 1470 Blake Street, Apt 6B, Denver, CO 80202. You can follow the shipment using the UPS tracking number on the UPS website to see the latest location and delivery updates.
Transcribed from Proof 1 · Screen recording at 0:08
| ✓ | Expected: Use the order system, not the knowledge base, and answer with the real status.Found: Fin used the order system, not the knowledge base, and returned the shipped status with matching carrier, tracking number, and delivery address. |
The request needed the order system, and the reply matched the connector's shipped status, carrier, tracking number, and delivery address. A single successful connector execution ties that answer to the order API, so this is a pass.
Single connector call. The connector shows one execution in the window, and it succeeded.
Shipping tip added. Fin also suggested checking UPS for live shipment updates, which goes beyond the order record.
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 | Intent understanding → | |
| Scenario | Request requires choosing the correct source or action → | |
| 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.