Does BlazeSQL keep two users on different data scopes separate?
BlazeSQL kept the two scopes apart. The full-access account returned plus for the membership question, while the restricted account refused to look the customer up and showed no SQL or result table.
1 of 1 test case passed
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.
Two accounts, two data scopesPassEvidence
Input 1: “What membership tier is Alice Prosser on?”
Input 2: “What membership tier is Alice Prosser on?”
Response 1 replies to Input 1.
Response 2 replies to Input 2.
Response to input 1 Alice Prosser is on the Plus membership tier, and her membership status is currently active. Response to input 2 I don't see a customers table in this database, so I'm unable to look up a customer by name (like "Alice Prosser"). The database doesn't appear to store customer names. If you have Alice Prosser's customer ID, I can look up her membership or subscription details using that! Alternatively, if customer names are stored somewhere I might be missing, let me know and I can try again.
Transcribed from Proof 2 · Screenshot
Transcribed from Proof 3 · Screenshot
| ✓ | Expected: Each account should answer from its own scope, and the narrower account should reveal nothing outside that scope.Found: The full-access account returned plus. The restricted account refused to look the customer up, showed no SQL or result table, and exposed no customer data. |
The wider account gave the expected membership tier, and the restricted account would not look the customer up, showed no SQL or result table, and exposed no customer data, so the required scope split was met.
Access panel layout. The access controls sit in the same panel that searches tables and columns.
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 | Data Access Control → | |
| Scenario | Two users are given different data scope → | |
| Tool | BlazeSQL → |
Global scenario definition → · Global capability definition → · BlazeSQL 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.