AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 20 November 2026

Can Extend AI extract repeated records from a document?

Extend AI returned the three line items on the invoice page as three records, each with its own description, item code, quantity, unit price and amount, with nothing dropped, duplicated or placed on the wrong record. The subtotal, VAT and total due lines below the table were not returned as records.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
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 is based on this test case.

Repeated set with correct associationPassEvidence
What we sent

In Extend AI's Extract Playground, we extracted page 3 of the invoice with a line-item schema of five fields: description, item code, quantity, unit price and amount.

Input 1Document (PDF)
Input PDF: the three-page invoice whose third page holds the goods table
Open the PDF ↗
Input 2File (JSON)
Extraction schema: a list of line items, each with five text fields
JSON
{
  "type": "object",
  "properties": {
    "line_items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "description": { "type": ["string", "null"] },
          "item_code": { "type": ["string", "null"] },
          "quantity": { "type": ["string", "null"] },
          "unit_price": { "type": ["string", "null"] },
          "amount": { "type": ["string", "null"] }
        },
        "required": ["description", "item_code", "quantity", "unit_price", "amount"],
        "additionalProperties": false
      }
    }
  },
  "required": ["line_items"],
  "additionalProperties": false
}
Open the JSON file ↗
What the tool returned
Text
{"amount": "£680.00", "quantity": "2", "item_code": "DP-2210", "unit_price": "£340.00", "description": "Dosing pump, 240V"}, {"amount": "£144.00", "quantity": "3", "item_code": "CT-1040", "unit_price": "£48.00", "description": "Chemical feed tubing, 10m coil"}, {"amount": "£215.00", "quantity": "1", "item_code": "FS-3302", "unit_price": "£215.00", "description": "Inline flow sensor"}

Returned JSON: the three line items with all five fields

Copied from Output file (JSON), line_items

Open the whole JSON file ↗
Expected vs. Found
✓Expected: Every record on the page with correct values, each value bound to its own record: none dropped, none duplicated, none on the wrong record.Found: It returned three records, the page's three goods rows, each with its own code, quantity, unit price and amount; the subtotal, VAT and total due lines were not records.
Supporting proof
Proof 1Screenshot
Screenshot: invoice page 3 beside the product's three-row results table
Open original ↗
Why this result

The test required every genuine record, with correct values bound to the right record. The page holds three goods rows, and the product returned exactly those three with all five fields on their own rows and left the summary lines out, so it is a Pass.

Tested by Rugved Nichite · evidence dated 17 November 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
Extend AI
Build or version
Not exposed by the hosted product
Surface
Web app
Set up before the run
The test needed one page with a small set of genuine records: page 3 of a three-page invoice, whose goods table holds three line items, each to be extracted into five fields (description, item code, quantity, unit price, amount).
Multifile
off
Tested
17 November 2026 · Rugved Nichite

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 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.

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
20 November 2026First publishedStructured Document Extraction 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/structured-document-extraction/results/extend-ai/a-repeated-set-of-records · 1 pass · 0 fail · coverage 1/1 · graded 2026-11-20

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.

Input 1 · Document (PDF) ↗application/pdf · 176 KB
Input 2 · File (JSON) ↗application/json · 1 KB
Output file (JSON) ↗application/json · 1 KB
Proof 1 · Screenshot ↗image/png · 124 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input 1 · Document (PDF)89fb14d7c0897bbfef47ffa3aa3930ee7eccf62c8a9430710d1906598c9bdfec
Input 2 · File (JSON)06828427e2072da28e0bf55c93df0293282314915caab0403775bdaea49925c1
Output file (JSON)fd2976da08263579fb7283ba34238264313dd6194016a66483758b86e0f4ad39
Proof 1 · Screenshotdbeba0004302831714df908d3df1bd14149e4a5a798bc0c31d8f876e44795e0b