Can FutureSmart Database Agent save an answer a user just got?
FutureSmart Database Agent did not let a user save an answer and reopen it later. The answer view showed viewing, filtering, charting, CSV export, thumbs, and copy controls, but no saved-answer destination.
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 is based on this test case.
Saved answer reopened in a new sessionFailEvidence
“Show me our monthly order count for the last 3 months, as of September 2, 2026.”
Monthly Order Count (as of September 2 2026) The query returned the number of orders placed in each month within the three-month window ending on September 2 2026 (June 2 - September 2 2026). The counts are: Key insight: August 2026 had the highest order volume (38 orders) in the period, while the partial month of September 2026 shows 12 orders up to the 2nd of the month. All figures are taken directly from the database query results. ORDER_MONTH | ORDER_COUNT 2026-09-01T00:00:00+00:00 | 12 2026-08-01T00:00:00+00:00 | 38 2026-07-01T00:00:00+00:00 | 21 2026-06-01T00:00:00+00:00 | 20 Showing 1-4 of 4 (rendered in the Table view of a Table/Chart toggle, with Table selected)
Transcribed from Proof 1 · Screenshot
Every message the tool sent, in order (3)
- Progress message
Generated SQL SELECT date_trunc('month', placed_at) AS order_month, COUNT... | Read table orders | Returned 4 rows
- Final response
Monthly Order Count (as of September 2 2026) The query returned the number of orders placed in each month within the three-month window ending on September 2 2026 (June 2 - September 2 2026). The counts are: Key insight: August 2026 had the highest order volume (38 orders) in the period, while the partial month of September 2026 shows 12 orders up to the 2nd of the month. All figures are taken directly from the database query results. ORDER_MONTH | ORDER_COUNT 2026-09-01T00:00:00+00:00 | 12 2026-08-01T00:00:00+00:00 | 38 2026-07-01T00:00:00+00:00 | 21 2026-06-01T00:00:00+00:00 | 20 Showing 1-4 of 4 (rendered in the Table view of a Table/Chart toggle, with Table selected)
- Generated query · not part of the answer
SELECT date_trunc('month', placed_at) AS order_month, COUNT(*) AS order_count FROM orders WHERE placed_at >= timestamp '2026-09-02 00:00:00+00' - interval '3 months' AND placed_at < timestamp '2026-09-02 00:00:00+00' GROUP BY date_trunc('month', placed_at) ORDER BY order_month DESC
| ✗ | Expected: Reopening should reproduce the same answer and make clear it is the same question.Found: No save path or saved-answer destination appears, so nothing can be reopened as a saved item. |
It is a Fail because the task requires a separate saved answer that can be reopened in a new session. The visible controls show viewing, filtering, CSV export, and past conversations, but no saved-answer area.
Export is not save. CSV preview is available, but it is only an export and not a saved answer.
Because there was no way to save the answer, the steps that would reopen it in a new session were not run.
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 Database Agents → | 28 scenarios · 11 tools |
| Capability | Reporting → | |
| Scenario | The user wants to keep an answer they just got → | |
| 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.