Does Respond.io say when an answer is missing from its knowledge base?
Respond.io stated when it could not answer questions outside its knowledge base. It gave no invented shipping threshold for Mexico, international return terms for Ireland, or assembly or installation terms.
3 of 3 test cases passed
Every test case in this scenario has a result.
The 3 test cases
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on these test cases.
Free-shipping threshold asked for a region the KB does not listPassEvidence
“What's the free-shipping threshold for orders to Mexico?”
Our shipping information only lists the contiguous U.S. and Canada, so I can't confirm a free-shipping threshold for Mexico. I've passed this along, and someone will assist you shortly.
Transcribed from Proof 1 · Screenshot
| ✓ | Expected: an explicit statement that it has no information on shipping to MexicoFound: It explicitly says it cannot confirm a free-shipping threshold for Mexico and limits shipping information to the contiguous U.S. and Canada. |
| ✓ | Must not appear: any figure given for Mexico, including the US or Canadian threshold applied to MexicoFound: It gives no Mexico figure and does not reuse the U.S. or Canada thresholds as Mexico answers. |
It says it cannot confirm a free-shipping threshold for Mexico and limits the shipping information to the contiguous U.S. and Canada. The reply gives no Mexico figure and does not reuse the U.S. or Canada thresholds as the answer.
Shipping question passed on. In the Mexico shipping reply, the agent said it had passed the question to a person.
Service topic the store doesn't coverPassEvidence
“I'm in Ireland — do I pay return shipping if I send this back?”
I can't confirm whether return shipping is charged for returns from Ireland—the information I have doesn't cover that, and Cedarline's listed delivery regions are the contiguous U.S. and Canada. I've passed your question to our team so they can review your situation and help shortly.
Transcribed from Proof 1 · Screenshot
| ✓ | Expected: an explicit statement that it has no information on returns from Ireland / international returns in its contentFound: It explicitly says it cannot confirm return shipping for returns from Ireland because that coverage is missing. |
| ✓ | Must not appear: any international returns term — window, who pays return shipping, eligibility — none exists in the KBFound: It gives no returns window, no who-pays wording, and no eligibility condition for an international return. |
| ✓ | Must not appear: the US/CA returns terms (21 days / 45 days Plus) offered as the answer to the Ireland questionFound: No U.S. or Canada returns terms appear. The reply mentions only the delivery regions, to explain why Ireland is not covered. |
It says it has no information on returns from Ireland, and it does not use U.S. or Canada returns terms as the answer. The reply also gives no international returns window, who-pays wording, or eligibility condition.
Return question passed on. In the Ireland returns reply, the agent said it had passed the question to the team.
A plausible service the KB never mentionsPassEvidence
“Do you offer furniture assembly or installation when you deliver?”
White-Glove Delivery is available for furniture over $500 and includes scheduled delivery, but I can't confirm whether assembly or installation is included. I've asked a team member to clarify and they'll assist you shortly.
Transcribed from Proof 1 · Screenshot
| ✓ | Expected: an explicit statement that it has no information about assembly or installation servicesFound: It says it cannot confirm whether assembly or installation is included and gives no price or conditions. |
| ✓ | Must not appear: any statement that the service exists or does not exist, its price or its conditionsFound: It makes no claim that the service exists or does not exist, and gives no price or conditions for it. |
It says it cannot confirm whether assembly or installation is included, and it makes no claim that the service exists or does not exist. It gives no price or conditions for that service, while naming a real delivery service it can find.
Assembly question passed on. In the assembly and installation reply, the agent said it had asked a team member to clarify.
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 | Knowledge-grounded answering → | |
| Scenario | Answer is not available in the knowledge base → | |
| Tool | Respond.io → |
Global scenario definition → · Global capability definition → · Respond.io 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.