Extracting data from aging reports
Every accounting package prints an aging report of receivables or payables, each with its own columns and bucket boundaries. Asset-based and small business lenders collect one from each borrower every month, exported as a PDF or spreadsheet and uploaded to the lender's portal.
Credit analysts need the total balance, each aging bucket and the customers behind the largest balances. Each month the borrowing base calculation counts current receivables as eligible collateral, and excludes balances older than the lender's cutoff.
What makes aging reports hard
Buckets end in different places
One report's oldest bucket is over 60 days and another's over 90 or 120, so the same column position can carry a different age.
Every cell feeds two totals
Each customer's buckets sum to its row total, and each bucket column sums to the total row, so every cell sits inside two checks.
Empty cells printed many ways
Accounting packages mark an empty bucket with a dash, a blank or a zero, and the three often appear in the same report.
Parse, extract, verify
Parse
Parse turns the document into reading-order Markdown and a hierarchy of blocks (text, tables, figures), and grounds each block to its exact location on the page.
Extract
You define the fields in a JSON schema, and Extract returns their values in a consistent, structured format, each linked back to where it appears in the Markdown.
Verify
Each value links back to where it appears, down to the character range in the Markdown, and the page and bounding box in the source document, so every result can be verified.
One AR and AP aging report, end to end
About this document: A sample accounts receivable aging report published by Empire State Development, New York State's economic development agency, for applicants to its lending program. One portrait page: a ruled table of customer rows under four aging buckets, a total row, and a short tip about accounting software. Page 1 is featured. Every customer and amount is specimen data.
Processing objective: The objective is to read the total row as one statement of the receivables. It gives how much is owed in all, and how that sum splits across the aging buckets. Each bucket's total grounds to its own cell, and together they add up to the total balance.
Demonstration fields: Total accounts receivable, Current, 1-30 days past due, 31-60 days past due, Over 60 days past due
The document
1 page
Page 1shown below
Where each value came from
totals.total_balance
{
"value": 11200,
"page": 1,
"range": {
"end": 1427,
"start": 1420
},
"box": {
"xmin": 0.49154,
"ymin": 0.53933,
"xmax": 0.56895,
"ymax": 0.568
}
}totals.current
{
"value": 7000,
"page": 1,
"range": {
"end": 1442,
"start": 1436
},
"box": {
"xmin": 0.56894,
"ymin": 0.53933,
"xmax": 0.64155,
"ymax": 0.56802
}
}totals.days_1_30
{
"value": 3000,
"page": 1,
"range": {
"end": 1457,
"start": 1451
},
"box": {
"xmin": 0.64155,
"ymin": 0.53933,
"xmax": 0.70898,
"ymax": 0.56803
}
}totals.days_31_60
{
"value": 900,
"page": 1,
"range": {
"end": 1471,
"start": 1466
},
"box": {
"xmin": 0.70897,
"ymin": 0.53933,
"xmax": 0.77102,
"ymax": 0.56805
}
}totals.over_oldest_bucket
{
"value": 300,
"page": 1,
"range": {
"end": 1485,
"start": 1480
},
"box": {
"xmin": 0.77101,
"ymin": 0.53933,
"xmax": 0.8645,
"ymax": 0.56807
}
}How to try it yourself
Everything on this page is reproducible. The sample, its schema, and the Parse and Extract API outputs are published. You can repeat the same two calls from whichever surface you already build on.
- Claude Skilldescribe the job; the agent writes it
- CLIno code at all
- MCPexpose ADE docs as an agent tool
- REST APIany language
- Pythonlandingai-ade
- TypeScriptlandingai-ade
Documents into data
Accurate
The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.
Auditable
Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.
Agentic
Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.
API-first
Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.
Affordable
Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.
Enterprise-grade
Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.
Built for high-volume, high-throughput production
- Zero data retention
- Priority rate limits
- Enhanced support
- VPC and on-prem deployment
Available on Team and Enterprise plans.
