Can Botpress continue an earlier conversation when a customer comes back?
Botpress did not continue the earlier return conversation when the customer came back. After reopening, it asked again for the order number and item, even though session 1 had already established them.
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 don't remember the date. I just want to return it”
Input 3: “12th september”
Input 4: “September 12, 2026”
Input 5: “yes”
Input 6: “No longer needed”
Input 7: “I'm following up on my return.”
Response 1 answers Input 1.
Response 2 answers Input 2.
Response 3 answers Input 3.
Response 4 answers Input 4.
Response 5 answers Input 5.
Response 6 answers Input 6.
Response 8, the final response, answers Input 7.
I can help with your return follow-up. Please provide your order number and the name of the item you want to return.
Transcribed from Proof 1 · Screen recording at 2:18
Every message the tool sent, in order (8)
- Response to input 1
Hi—welcome to Cedarline support. I'm Cedarline's artificial intelligence support agent, and I can help with your return request for order 41455 and the sofa you ordered by mistake. When was the sofa purchased?
- Response to input 2
I understand. To check whether the sofa is eligible for return, I still need the purchase date—or at least an approximate month and year. You may be able to find it in your order confirmation or payment record. If you can't locate it, I can connect you with a human representative for help.
- Response to input 3
Thanks. Was the sofa purchased on September 12, 2026, or September 12 of another year? I need the year to check whether it falls within Cedarline's return window.
- Response to input 4
Thank you. Order 41455 was placed on September 12, 2026. Cedarline's standard return window is 21 days, while Cedarline Plus orders have an extended 45-day window. Because this is past the standard window, was the order placed while you had an active Cedarline Plus membership?
- Response to input 5
Thank you. Since the order was placed while your Cedarline Plus membership was active, the sofa is within the 45-day return window and is eligible for return. Please briefly tell me the reason for the return—for example, ordered by mistake, damaged, incorrect item, or no longer needed.
- Response to input 6
Your return request is summarized as follows:
- Order: 41455
- Item: Sofa
- Purchase date: September 12, 2026
- Cedarline Plus: Active when the order was placed
- Eligibility: Eligible under the 45-day Cedarline Plus return window
- Reason: No longer needed
The next step is for a Cedarline representative to provide the return instructions and shipping-label details. Once the sofa is received and passes warehouse inspection, the refund is typically issued within 5–7 business days. The refund timeline then depends on the original payment method—for example, 5–7 business days for a credit or debit card and 3–5 business days for PayPal.
Show the reply as returned (Markdown)
Your return request is summarized as follows: - Order: 41455 - Item: Sofa - Purchase date: September 12, 2026 - Cedarline Plus: Active when the order was placed - Eligibility: Eligible under the 45-day Cedarline Plus return window - Reason: No longer needed The next step is for a Cedarline representative to provide the return instructions and shipping-label details. Once the sofa is received and passes warehouse inspection, the refund is typically issued within 5–7 business days. The refund timeline then depends on the original payment method—for example, 5–7 business days for a credit or debit card and 3–5 business days for PayPal.
- Response 7
I understand. A Cedarline representative needs to assist with the return shipping-label instructions and complete the return process.
- Final response
The final response, printed above.
| ✗ | Expected: Keeps the return conversation going without making the customer repeat the key details.Found: The reopened widget asked again for the order number and item, even though session 1 had already set them. |
The customer was supposed to resume the return without repeating key details. Instead, the reopened widget asked again for the order number and item that session 1 had already established.
Hand-off first. The first session ended in a human hand-off, and reopening started on a fresh welcome screen instead of the earlier thread.
Repeat prompt. The follow-up still asked for the order number and item name instead of continuing the open return.
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 | Botpress → |
Global scenario definition → · Global capability definition → · Botpress 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.