Does Zendesk AI's analytics match what actually happened?
Zendesk AI's reporting overview for 23 September to 15 October 2026 showed 50 conversations and 11 assisted escalations, and all 25 of our earlier test conversations, including the three escalation tests, appear in its conversation logs. Its totals contain our runs; the extra conversations are other traffic on the same agent.
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.
Product's counts vs our recordsPassEvidence
No message was sent: the counts were read from Zendesk's reporting overview and conversation logs.
The tool's response has no text to quote: it is what the evidence under Proof shows.
Proof 1 · Screen recording · ▶ 3:56–3:59
| ✓ | Expected: The product's conversation and escalation numbers agree with our own record of the test runs.Found: The dashboard reported 50 conversations and 11 assisted escalations for the period; our record holds 25 conversations, 3 of them escalations, and each appears in the conversation logs. |
The case asks whether the product's counts agree with our record of the runs. Every one of our 25 conversations and 3 escalations is inside its totals and none of its counts is below ours, so it passes. The agreement is containment: the dashboard counts all traffic on the agent, not just our tests.
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 | Analytics and observability → | |
| Scenario | Reported analytics match what actually happened → | |
| 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.