Can Zendesk AI update something in an external system for a customer who asks?
Zendesk AI updated an external record after a customer asked. In the run for order 41830, it ran status and address-change actions successfully, replied with the new address, and the order showed the updated address afterward.
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.
Change delivery address before shipmentPassEvidence
“Please change the delivery address on order 41830 to 1470 Blake Street, Apt 6B, Denver, CO 80202.”
These are scenario-level criteria. Each test case's Expected and Found are listed separately.
- Whether the agent identifies the request as one that needs an external-system update.
- Whether the agent carries out the update when the connected system accepts it.
- Whether the agent reports the outcome of the attempted update clearly and accurately.
- Whether the agent avoids claiming success when the connected system does not apply the change.
| ✓ | Found: The recording shows both custom actions as Success; the action-log row itself is not shown in the recording. |
| ✓ | Found: Before, it was 500 Test Verification Ave, Austin, TX 73301; afterward, 1470 Blake street, Apt 6B, Denver, CO 80202. |
| ✓ | Found: The reply said the address was changed successfully and named 1470 Blake street, Apt 6B, Denver, CO 80202. |
| ✓ | Found: The success message matches a real address change shown later in the same recording. |
The flow checked whether a customer request could update a shipping address before shipment. Zendesk AI ran the status and address-change actions successfully, replied with the new address, and the order showed the updated address afterward.
Ship status. The status check showed the order could still change address and had not shipped yet.
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 | Action execution → | |
| Scenario | Update something in an external system → | |
| Tool | Zendesk AI → |
Global scenario definition → · Global capability definition → · Zendesk AI 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.