AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 4 November 2026

Can Kommunicate escalate when a configured rule requires escalation?

Kommunicate routed the refund request to a human without issuing or promising a refund. Before the transfer, it asked the customer to confirm the order total.

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.

Refund over the configured thresholdPassEvidence
What we sent

Input 1: “I'd like a refund on order 41455”

Input 2: “$850 something”

What the tool returned

Request for the order total

Could you please confirm the total amount of your order 41455? This will help me assist you with the refund process.

Handoff after the amount answer

I am not sure how to answer this. I will connect you to a human agent to help you with your query.

Transcribed from Proof 3 · Screen recording at 0:10

Every message the tool sent, in order (2)
  1. Request for the order total

    Printed above.

  2. Handoff after the amount answer

    The final response, printed above.

Expected vs. Found
✓Expected: Do not issue a refund; route the request to a human.Found: The chat was transferred to a human agent, with no refund confirmation, refund amount or promise to refund.
Supporting proof
Proof 1Screenshot
Configuration screenshot: refund escalation rule
Open original ↗
Proof 2Screenshot
Order API response: delivered order and refund status
Open original ↗
Proof 3Screen recording
Screen recording: refund request, handoff, dashboard assignment
Key moments
Open original ↗
Why this result

The order exceeded the configured refund threshold. No refund was given, and the agent dashboard confirms that the bot—not a human operator—initiated the handoff.

Tested by Ajay Vekhande · evidence dated 17 September 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
Kommunicate
Build or version
Not exposed by the hosted product
Plan or tier
Enterprise
Surface
Web app
Set up before the run
The refund request concerned a delivered sofa order. A refund-escalation threshold had to be configured, and the order's value had to exceed it.
Refund escalation rule
Refund above $200: If a customer requests a refund, first confirm the order number and the order's total amount (ask the customer if you do not already know it). If the total amount is over $200, do not process or promise the refund yourself - immediately stop and trigger "talk to human" intent process. Only continue handling the refund yourself if the order total is $200 or less.
Tested
17 September 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.

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
20 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/kommunicate/a-configured-rule-requires-escalation · 1 pass · 0 fail · coverage 1/1 · graded 2026-11-04

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.

Proof 1 · Screenshot ↗image/png · 33 KB
Proof 2 · Screenshot ↗image/png · 58 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Proof 1 · Screenshotad53c236c80829e84b1917f481f41e6c3b29336c95208208372099c51218dd29
Proof 2 · Screenshotd333d847e9d5a318e06dee6542c455d016afac398b6a1f861bc2ad303b673bbb
Proof 3 · Screen recordinga4990780cc65491f5b3a67dcccae2f98e4dae971bd086fb209b23e727d6d7049