AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 20 November 2026

Do the analytics Anomaly AI reports match what actually happened?

Anomaly AI reports no count of the questions asked and no split between answered and unanswered ones, so there was no total to match against the five questions run, two of them unanswerable. Its only usage figures are credits, which are not questions.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
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.

Reported totals include the unansweredFailEvidence
What we sent

The project was shared with the second account in a two-member workspace.

Input 1 · First account: “As of September 2, 2026, what's our total revenue in the last 30 days?”

Input 2 · First account: “What's our most common payment method?”

Input 3 · First account: “How many complaints have we received on social media this month?”

Input 4 · Second account: “How many customers currently have an active subscription?”

Input 5 · Second account: “What's our net promoter score for last quarter?”

What the tool returned

The tool's response has no text to quote: it is what the evidence under Proof shows.

Proof 1 · Screen recording · ▶ 2:28–2:30; ▶ 2:10–2:12

Expected vs. Found
✗Expected: Reported totals that match the five questions run, including the two that could not be answered, not only the successes.Found: The usage page showed 61 credits used, 59.4 and 1.6 per member, including earlier work; recent activity listed only a project share and a member joining. No view counted questions.
Supporting proof
Proof 1Screen recording
Screen recording: the usage, billing and recent activity pages, and a sweep of other views
Key moments
Open original ↗
Why this result

The test needed totals showing five questions, two unanswerable. The views opened report credits, not a question count. It is a Fail, not a plan limit: the account had Pro access, which the billing page labels Free Trial with Pro's 1,000-credit allowance, and no plan describes question reporting.

Tested by Anchal Rana · evidence dated 3 November 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
Anomaly AI
Build or version
Not exposed by the hosted product
Plan or tier
Pro
Surface
Web app
Set up before the run
Two people in one shared workspace had to ask five questions about the store's commerce data, two of them unanswerable; the product's own reporting views then had to be read for totals to compare with those five.
Workspace members
2
Tested
3 November 2026 · Anchal Rana

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
21 November 2026First publishedAI Database Agents 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-database-agents/results/anomaly-ai/analytics-accuracy · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-20

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 recordingbc0654575b7f38e594bafd8fc6f8d76b5f5db1528fb1b9346ae79dac86940a6e