Does Botpress keep context when a customer switches languages mid-conversation?
Botpress kept the conversation context when the customer switched from French to English. The same thread shows a French return-policy answer first, then an English follow-up that repeats the 45-day Plus window and the 21-day standard window.
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.
Language switch to English mid-conversationPassEvidence
Input 1: “Quelle est la politique de retour ?”
Input 2: “Okay, so if I have a Plus membership, I'll have a 45-day return window, right?”
The tool's reply is shown in the evidence under Proof.
Response 1 replies to Input 1.
Response 2 replies to Input 2.
Response to input 1 Bonjour Alice — je suis l'assistant d'intelligence artificielle de Cedarline. En tant que membre Cedarline Plus, vous bénéficiez d'un délai de retour prolongé de 45 jours, au lieu du délai standard de 21 jours. Response to input 2 Yes. As a Cedarline Plus member, you have a 45-day return window instead of the standard 21 days for orders placed while your membership is active—even if the order is delivered after you cancel, as long as it was placed during the active membership period.
Transcribed from Proof 1 · Screenshot
Transcribed from Proof 1 · Screenshot
| ✓ | Expected: Stay in English without losing the conversation context.Found: The follow-up is wholly in English and keeps the earlier 45-day Plus window and 21-day standard window, showing the thread stayed connected. |
The reply had to stay context-aware after the language change. The first answer is in French; the follow-up is entirely in English and preserves the earlier 45-day Plus return window, so the switch did not break the thread.
Context carried forward. The follow-up is self-contained and still restates the earlier Plus return window.
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 | Multilingual support → | |
| Scenario | Customer switches languages during the conversation → | |
| 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.