Can FutureSmart Document Intelligence refuse when content is removed from the source?
After deletion and refresh, FutureSmart Document Intelligence no longer returned the removed document in the query results or citations, and it said the retrieved documents do not identify an approved supplier for the H-clamp bracket. The evidence shows four surviving sections in the after capture, with the deleted document absent from them.
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 counts this row.
Sole-source document deleted, then queried after a refreshPassEvidence
“Who is the approved supplier of the H-clamp bracket?”
answer: The retrieved documents do not identify an approved supplier for the H-clamp bracket.
Text file showing before-and-after retrievals for the H-clamp supplier query.
Copied from Output file (text), line 340
Open the text file ↗These are scenario-level criteria. Each test case's Expected and Found are listed separately.
- Whether the content was returned successfully before it was removed from the source.
- Whether the removed content is still returned after the source no longer contains it.
- Whether the system stops surfacing the removed content once removal has taken effect.
| ✓ | Found: The removed document disappeared from results and citations, and the answer said no approved supplier was identified. |
The post-delete query returned only the remaining documents, with the removed document’s id and supplier name absent. The answer therefore said no approved supplier was identified, matching both the disappearance and the fallback response.
Queued delete job. Delete status stayed queued for about 30 seconds even after the removal took effect in the documents list and retrieval. A caller watching only the status would think the refresh had not finished.
Refusal names retrieved docs. The answer refers to the retrieved documents, not the whole collection. That wording matches the evidence because it only claims what the retrieval showed.
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 | Managed RAG → | 15 scenarios · 5 tools |
| Capability | Knowledge Sync → | |
| Scenario | Content is removed from the source → | |
| Tool | FutureSmart Document Intelligence → |
Global scenario definition → · Global capability definition →
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.