Can Zendesk AI continue an earlier conversation in a follow-up session?
Zendesk AI did not continue the earlier return conversation in the follow-up session. In the second session, the agent answered generically and then gave support channels instead of naming the earlier order or sofa, while the earlier exchange stayed in the same thread.
1 of 1 test case failed
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.
Return discussed in session 1, followed up in session 2FailEvidence
Input 1: “Hi, I'd like to return order 41455 – I ordered the wrong sofa”
Input 2: “I'm following up on my return.”
Input 3: “status of return”
Response 1 replies to Input 1.
Response 2 replies to Input 2.
Response 3 replies to Input 3.
Response to input 1 I'm sorry for the inconvenience. If order 41455 contained the wrong sofa, report it within 7 days of delivery with photos of the item and packaging. No restocking fee or normal return window applies. Support can arrange a replacement, if in stock, or a full refund including original shipping. Contact support via website/app live chat, support@cedarline.com, or 1-800-CEDAR-01, Mon–Sat, 9am–7pm MT. Response to input 2 Would you like to check the status of your return or your refund? Response to input 3 You can check your return status through Cedarline's website, mobile app, live chat, email, or phone. Live chat is fastest, typically responding within 5 minutes. Email support@cedarline.com takes up to 24 hours; call 1-800-CEDAR-01 Mon–Sat, 9am–7pm MT. I'm sorry for any inconvenience.
Transcribed from Proof 1 · Screen recording at 0:07
Transcribed from Proof 1 · Screen recording at 0:47
Transcribed from Proof 1 · Screen recording at 1:10
| ✗ | Expected: Continues the return thread without the customer having to restate itFound: The follow-up reply is generic, then the agent points to support channels; the earlier return details are not named in either reply. |
It fails because the follow-up reply stays generic and then sends the customer to support channels instead of continuing the earlier return details already in the thread.
Thread stayed open. The earlier return messages stayed in the same widget thread after the widget was reopened.
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 | Conversation continuity → | |
| Scenario | Earlier conversation/session needs to be continued → | |
| 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.