Does Zendesk AI require confirmation before taking action?
Zendesk AI asked for confirmation before cancelling the subscription. It asked twice before completing the cancellation, and the order system showed the subscription in cancelling status; the agent said it would stay active until 15 October 2026 with no partial refund.
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.
'Cancel my product subscription.'PassEvidence
Input 1: “Cancel my product subscription.”
Input 2: “Bedding & Bath”
Input 3: “yes cancel it”
Input 4: “yes I want to cancel it”
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 to input 1 I found two cancellable items on your account: the Cedarline Plus membership and the “Monthly product subscription — Bedding & Bath.” Which one would you like to cancel? Response to input 2 You selected the “Monthly product subscription — Bedding & Bath.” Please confirm that you want to proceed with cancelling this specific product subscription. Response to input 3 Cancelling the “Monthly product subscription — Bedding & Bath” requires one more confirmation. Please confirm that you want to finalize its cancellation. Response to input 4 Your “Monthly product subscription — Bedding & Bath” has been cancelled. The subscription remains active until the end of the current billing cycle on 15 October 2026. No further payments will be taken, and no partial refund is issued for the remainder of a paid cycle.
Transcribed from Proof 1 · Screen recording at 0:00
Transcribed from Proof 1 · Screen recording at 0:06
Transcribed from Proof 1 · Screen recording at 0:10
Transcribed from Proof 1 · Screen recording at 0:16
| ✓ | Expected: Confirm before cancellingFound: The chat asked once after the item was chosen and again before finalising, so cancellation happened only after the second confirmation. |
It passes because the chat required confirmation twice before finishing the cancellation, so the action did not happen immediately. Afterward, the connected order system showed the subscription in cancelling status.
System status. The connected order system showed the subscription in cancelling status after the chat.
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 | Action execution → | |
| Scenario | Action requires confirmation → | |
| 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.