AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 8 October 2026

Can FutureSmart Document Intelligence tell when the knowledge base has no answer?

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 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are on the row.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above counts this row.

Reasonable question no document answersFailEvidence
What we sent

“How much paid parental leave does Fenwake give?”

What the tool returned
Text
score=1.0000  document_id=09c99644-e630-44a4-81f5-636ed80d942c
Extracted Text: Employee Handbook
Fenwake Instruments Ltd - all locations
1. Working here
This handbook sets out the terms that apply to everyone employed by Fenwake Instruments Ltd, whether based at the Bristol workshop, at the Avonmouth calibration laboratory, or working from a customer site or vessel. It forms part of your contract. Where a term is set out in your written statement of particulars and also here, the written statement governs.
2. Hours of work
Standard hours are 37.5 a week, worked between 08:00 and 18:00, Monday to Friday. Workshop staff work a 07:30 start by agreement with the workshop manager. Anyone rostered to the out-of-hours duty engineer rota is paid a standby allowance for each week on the rota, and an hourly rate for any hour actually worked while on standby.
2.1 Time recording
Hours are recorded against a job number on the day they are worked. A job number is required for chargeable work, for internal projects and for training. Corrections are made by the line manager rather than by editing a submitted week.
3. Annual leave
Full-time employees accrue 26 days of annual leave in each complete leave year, which runs from 1 April to 31 March. Part-time employees accrue pro rata. Leave accrues from the first day of employment and may be taken during the probation period with the line manager's agreement.
3.1 Booking leave
Annual leave is requested in the rota system and confirmed by the line manager. Requests are considered in the order they are received. Service operations will decline a request that would leave the duty engineer rota uncovered, and will say so within five working days so that alternative dates can be chosen.
3.2 Carry-over
Up to five days of untaken annual leave may be carried into the next leave year, and must be taken by 30 June. Anything beyond five days is carried over only where leave could not be taken because of a business requirement, and only with the written agreement of a director.
3.3 Leave on leaving

score=0.5333  document_id=09c99644-e630-44a4-81f5-636ed80d942c
3.3 Leave on leaving
On termination, accrued and untaken annual leave is paid in the final salary payment. Where more leave has been taken than accrued, the balance is deducted from that payment.
4. Sickness absence
Report sickness to your line manager before 09:00 on the first day, by telephone rather than by message. Absence of seven calendar days or fewer is self-certified on return. Longer absence requires a fit note. Company sick pay is paid at normal salary for the first four weeks of a continuous absence and at half salary for the following four weeks, after which statutory sick pay alone applies.
4.1 Return to work
Every absence is followed by a return-to-work conversation with the line manager. The conversation is recorded in one paragraph on the personnel file. Where an absence relates to a condition that affects offshore or diving work, occupational health is consulted before the employee returns to that work.
5. Expenses
Expenses are claimed monthly, with receipts, and reimbursed with the following month's salary. Mileage in a private vehicle is paid at the approved rate. Overnight accommodation is booked through the company travel account wherever possible; where it is not, a room is reimbursed at cost within the regional cap published on the intranet.
6. Notice
During probation, notice is one week on either side. After probation, notice is one month for most roles and three months for directors and for the head of service operations. The company may pay in lieu of notice.
7. Training and certification
Offshore survival and first-aid certification is renewed at company expense before it expires. Time spent in required training counts as working time. Where an employee leaves within twelve months of a discretionary course costing more than two thousand pounds, a proportion is recoverable, as set out in the training agreement signed before the course.
8. Conduct at sea and on customer sites

score=0.4167  document_id=09c99644-e630-44a4-81f5-636ed80d942c
8. Conduct at sea and on customer sites
On a vessel, the master's instructions take precedence over any instruction from Fenwake. On a customer site, the site's permit-to-work system governs. An employee who believes work cannot be done safely is expected to stop it, and will be supported for having done so.
9. Personal data
Personnel records are held for the duration of employment and for six years afterwards. Employees may ask to see their record at any time by writing to the operations director.

Transcript of the search and the control question, with the returned sections shown in full.

Copied from Captured file (text), lines 9–46

Open the text file ↗
Expected vs. Found
✗Expected: It should clearly show no match, such as no results or a clear score gap.Found: It returned three sections with a top score of 1.0000, matching the answerable query's shape.
Supporting proof
Proof 1Screenshot
Search request for the unanswerable question and its returned sections.
Open original ↗
Proof 2Screenshot
Chat answer saying the handbook does not specify paid parental leave.
Open original ↗
Why this result

The /search response was checked against the unanswerable question and the control query. The unanswerable query returned three sections with a top score of 1.0000, but the returned handbook sections do not answer it. The control query returned the answer in its top section.

Also observed on this row

Chat answer shown. The chat answer says the handbook does not specify any paid parental leave entitlement.

Tested by Vivek Tomar · evidence dated 7 September 2026

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.

Software that produced the output
FutureSmart Document Intelligence
Build or version
v1
Surface
API
Set up before the run
The corpus needed to have no document that contained or implied the answer. The question needed to be a reasonable one in the same topic area, but one the corpus could not answer.
Request parameters
default params — no top_k, no filters
Tested
7 September 2026 · Vivek Tomar

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

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.

from the publication record
23 October 2026First publishedManaged RAG v1

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/managed-rag/results/futuresmart-document-intelligence/answer-is-not-available-in-the-knowledge-base · 0 pass · 1 fail · coverage 1/1 · graded 2026-10-08

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.

Proof 1 · Screenshot ↗image/png · 491 KB
Captured file (text) ↗text/plain; charset=utf-8 · 11 KB
Proof 2 · Screenshot ↗image/png · 354 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Proof 1 · Screenshotc34c2fc62687987dd51d995321a4d7829096362176b2fb44f57d7b08763c3e3a
Captured file (text)ae4cd9178d14fb18d0e88d150227e87313c9614374573ae1201221e817018317
Proof 2 · Screenshot77ca8824c2bafa797e937718bb14b436ff17def9a7684161bd7cda7d9ca12a30