Does FutureSmart Database Agent find the right rows when the user's wording doesn't match how the values are stored?
FutureSmart Database Agent failed to bridge the user's wording to the stored value, and it returned an empty answer as if it were a fact. The generated SQL searched only for gift voucher phrasing and never referenced gift_card, while the answer text said no matching orders existed and suggested broadening the search. The capture cannot show table contents, so the stored values themselves were not visible.
1 of 1 test case failed
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 counts this row.
Category asked by the user's synonymFailEvidence
“Show me all orders paid with a gift voucher.”
SELECT id, customer_id, status, delivery_address, total_amount, currency, category, item_summary, city, state, postal_code, payment_method, shipping_cost, discount_total, carrier, tracking_number, placed_at, shipped_at, delivered_at, estimated_delivery, refunded_at, order_number FROM orders WHERE payment_method ILIKE '%gift_voucher%' OR payment_method ILIKE '%gift voucher%' OR payment_method ILIKE '%voucher%' LIMIT 10
Transcribed from Proof 1 · Screenshot
These are scenario-level criteria. Each test case's Expected and Found are listed separately.
- Whether it maps a natural synonym to the stored value it represents.
- Whether it returns the matching records rather than treating the question as unanswered.
- Whether it treats the wording difference as a translation problem, not as missing data.
| ✗ | Found: The answer presented no results instead of returning the matching records. |
The product searched only literal gift-voucher variants and answered that no results existed, instead of finding the stored matching value. The capture shows the generated SQL, the no-results answer, and no result grid or row count.
Follow-up search suggestion. The answer suggested checking payment_method values or broadening the search criteria.
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 row says which 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 row 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 Database Agents → | 28 scenarios · 4 tools |
| Capability | Question Answering → | |
| Scenario | The user's wording doesn't match how the values are stored → | |
| Tool | FutureSmart Database Agent → |
Global scenario definition → · Global capability definition → · FutureSmart Database Agent 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.