Tool in benchmark · Version 1

FutureSmart Document Intelligence in Managed RAG

Scenario-level performance from current published Results.

12Passed
3Failed
0No published Result yet

15 of 15 scenarios published

CapabilityScenariosResult
Citations0 pass · 1 fail · 1 of 1 published
Data Ingestion4 pass · 0 fail · 4 of 4 published
Grounded Generation3 pass · 0 fail · 3 of 3 published
Knowledge Sync3 pass · 0 fail · 3 of 3 published
Retrieval2 pass · 2 fail · 4 of 4 published
PassedFailedPublished, different test setNo published Result yet

Where FutureSmart Document Intelligence failed

3 of 15 graded scenarios. Open a Result to see the conversation and the evidence.

Citations

A claim in the answer traced back to its source

FutureSmart Document Intelligence does not link the answer claim to a supporting passage. The chat response had no citation marker or section reference, and the web Conversations view panel listed source files rather than the supporting passage; the top section matched the answer, but a conflicting 30-minute section also appeared.

View Result →
Retrieval

Answer is not available in the knowledge base

FutureSmart Document Intelligence fails this scenario on the /search surface. The unanswerable paid-parental-leave query returns three sections with a top score of 1.0000, and the returned handbook sections do not answer it. The control query on the same corpus also returns three sections with a top score of 1.0000, and its top section contains the answer. A separate /chat answer says the handbook does not specify any paid parental leave entitlement.

View Result →
Retrieval

Retrieval is scoped to part of the documents

FutureSmart Document Intelligence failed to keep retrieval scoped to the subset that did not hold the answer. Both restricted searches still returned the answering depot note first at score 1.0000.

View Result →

How FutureSmart Document Intelligence performed

Open a capability to explore its scenarios. Each row reports the test set in its published Result.

Citations1 fail
ScenarioPublished outcomesTest coverageResult
A claim in the answer traced back to its source
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

FutureSmart Document Intelligence does not link the answer claim to a supporting passage. The chat response had no citation marker or section reference, and the web Conversations view panel listed source files rather than the supporting passage; the top section matched the answer, but a conflicting 30-minute section also appeared.

1/1 assessed1/1 gradablePublished test setView Result →
Data Ingestion4 pass
ScenarioPublished outcomesTest coverageResult
A bad file in the upload
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence passed this upload scenario: it reported both bad PDFs as failures instead of ingesting them. The truncated file and the password-protected file were both rejected; the app said each could not be uploaded, and the API returned HTTP 500.

1/1 assessed1/1 gradablePublished test setView Result →
A cleanly scanned document
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence returned the OCR text from the cleanly scanned document. It returned the as-found bias, -0.037 psu, for certificate C-77413; separately, the scanned certificate was the top search hit.

1/1 assessed1/1 gradablePublished test setView Result →
A simple, clearly formatted table
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence passes this simple-table scenario in the checked case. The table shows Extended / Out-of-hours callout at 487, and the grounded answer gives the same amount. The captured table also shows the nearby values in the same section.

1/1 assessed1/1 gradablePublished test setView Result →
An ordinary digital text document
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence returned the calibration passage first, and the answer gave 22 months from the last calibration certificate. A 36-month warranty passage also appeared at a lower score and did not replace the calibration passage.

1/1 assessed1/1 gradablePublished test setView Result →
Grounded Generation3 pass
ScenarioPublished outcomesTest coverageResult
The retrieved material doesn't support an answer
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence declined to answer the unsupported paid parental leave question and gave no paid-leave figure. Its reply said the employee handbook did not specify any paid parental leave entitlement, and retrieval returned 27 sections with a top score of 1.0000.

1/1 assessed1/1 gradablePublished test setView Result →
The retrieved material supports an answer
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence produced an answer that is supported by the passages in view. The checked passage supports the out-of-hours acknowledgement timing, named duty engineer, telephone ownership confirmation, and written confirmation on request, with no unsupported additions in the graded check.

1/1 assessed1/1 gradablePublished test setView Result →
The retrieved sources disagree with each other
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence showed that the retrieved sources disagreed about the warranty period. It reported 24 months from delivery in the customer-facing sales pack and 36 months from delivery in the service-desk service pack, with both periods beginning at delivery.

1/1 assessed1/1 gradablePublished test setView Result →
Knowledge Sync3 pass
ScenarioPublished outcomesTest coverageResult
Content is removed from the source
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

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.

1/1 assessed1/1 gradablePublished test setView Result →
Existing content is changed
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence passed this changed-content scenario. Before the refresh it answered 11 working days; after the old B02 was deleted and the replacement ingested, it answered 6 working days, with the new file first and the old value absent.

1/1 assessed1/1 gradablePublished test setView Result →
New content is added to the source
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence found the newly added content after it was indexed. Before the add, it said the retrieved information did not state when the Tromso depot opens; after the bulletin was indexed, it answered 14 October 2026 and ranked that bulletin first.

1/1 assessed1/1 gradablePublished test setView Result →
Retrieval2 pass2 fail
ScenarioPublished outcomesTest coverageResult
Answer is available in the knowledge base
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence surfaced the supporting passage for the knowledge-base answer. The returned text matched the passage saying a Priority 1 fault reported outside business hours is acknowledged by a named duty engineer within 90 minutes, and the UI showed A01 first in Sources. Only four of eight source passages were visible in one capture, while the full notebook response was available in the attached text artifact.

1/1 assessed1/1 gradablePublished test setView Result →
Answer is not available in the knowledge base
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

FutureSmart Document Intelligence fails this scenario on the /search surface. The unanswerable paid-parental-leave query returns three sections with a top score of 1.0000, and the returned handbook sections do not answer it. The control query on the same corpus also returns three sections with a top score of 1.0000, and its top section contains the answer. A separate /chat answer says the handbook does not specify any paid parental leave entitlement.

1/1 assessed1/1 gradablePublished test setView Result →
Retrieval is scoped to part of the documents
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

FutureSmart Document Intelligence failed to keep retrieval scoped to the subset that did not hold the answer. Both restricted searches still returned the answering depot note first at score 1.0000.

1/1 assessed1/1 gradablePublished test setView Result →
The request uses different wording than the source
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

FutureSmart Document Intelligence handled the wording change and still returned the annual-leave answer. Search ranked the handbook passage first, and chat answered 26 days per complete leave year with part-time pro rata.

1/1 assessed1/1 gradablePublished test setView Result →

Reading these Results

Published evidence and test coverage answer different questions.

Publication availability

Which scenarios have a Result?

A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.

Test coverage

What does each Result cover?

Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.

Scenario scope

Out of 15 scenarios

The summary counts each of the 15 scenarios once. A scenario fails when any of its published test cases failed. “No published Result yet” means nothing is public for that scenario; it does not say whether FutureSmart Document Intelligence was tested on it.

FutureSmart Document Intelligence in Managed RAG | AI Demos