AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 28 October 2026

Does Respond.io ask the customer to confirm before it acts?

Respond.io asked the customer to confirm before it cancelled a subscription. Asked to cancel, it only looked the subscription up, named the plan and its monthly price, said the cancellation takes effect at the end of the billing cycle with no partial refund, and asked whether to proceed. It cancelled only after the customer said yes.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

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.

'Cancel my product subscription.'PassEvidence
What we sent

Input 1: “Cancel my product subscription.”

Input 2: “yes proceed”

What the tool returned

Answer: the confirmation question

I found your active Bedding & Bath subscription at $24.99/month, with the next billing date on November 8, 2026. Cancellation takes effect at the end of the current billing cycle, with no partial refund for the remainder of the paid cycle. Would you like me to proceed?

Answer after the customer said yes

Your Bedding & Bath subscription is cancelled. It will remain active until November 8, 2026, and no further payments will be taken. Anything else I can help you with?

Transcribed from Proof 1 · Screen recording at 0:02

Every message the tool sent, in order (2)
  1. Answer: the confirmation question

    Printed above.

  2. Answer after the customer said yes

    The final response, printed above.

Expected vs. Found
✓Expected: Asks the customer to confirm before it cancels the subscription.Found: It first looked up the subscription, named the Bedding & Bath plan at $24.99 a month and asked whether to proceed. It cancelled only after the customer said yes.
Supporting proof
Proof 1Screen recording
Screen recording: the cancellation chat, its actions in order, and the subscription's state afterwards
Key moments
Open original ↗
Why this result

It is a Pass because the confirmation came before any cancelling action. The agent only looked the subscription up, asked whether to proceed, and cancelled after the customer said yes. Its cancel action was set up to ask for explicit confirmation; the agent still had to ask before acting.

Tested by Ajay Vekhande · evidence dated 28 October 2026

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.

Software that produced the output
Respond.io
Build or version
Not exposed by the hosted product
Plan or tier
Growth (free trial)
Surface
Web app
Set up before the run
The customer had to have an active subscription that could be cancelled, here a Bedding & Bath plan, and the agent's cancel action had to work against the store's subscription system.
Cancel Subscription action instruction
Use this action when the customer wants to cancel a product subscription. First call List Subscriptions to find the matching subscription and confirm its ID and that can_cancel is true. Read back the plan name and price to the customer and get explicit confirmation before cancelling - this cancels immediately with no confirmation step on the API side.
Agent run mode
test mode
Tested
28 October 2026 · Ajay Vekhande

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

LevelNameScope
BenchmarkAI Customer Support Chatbots →26 scenarios · 14 tools
CapabilityAction execution →
ScenarioAction requires confirmation →
ToolRespond.io →

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.

from the publication record
16 November 2026First publishedAI Customer Support Chatbots v1

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/ai-customer-support-chatbots/results/respond-io/action-requires-confirmation · 1 pass · 0 fail · coverage 1/1 · graded 2026-10-28

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.

Proof 1 · Screen recording5d1590afb8f86d79202cc333b3cc54bd77125f73b87a6ecd39a4c2df0cb540b7