Extracting data from invoices
Every business that buys anything receives invoices, and no two suppliers format them alike. A mid-sized accounts payable team handles several thousand a month, arriving as email attachments and as photographs of paper. Each one has to be matched to a purchase order before it can be paid.
Accounts payable needs the supplier, the invoice number, every line item and the amount due. An ERP matches those against the open purchase order, posts the invoice to the general ledger, and schedules it into a payment run.
What makes invoices hard
Every supplier has a different layout
Template extraction needs one template per supplier. Every new vendor is onboarding work, and every redesign breaks what already worked.
Line item tables break across pages
A multi-page invoice splits its line item table across sheets, repeating the headers on each one and carrying subtotals forward.
Normalized values, original evidence
Dates, currencies and tax identifiers must come out in one machine-readable form. An auditor still wants the string exactly as the supplier printed it.
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 invoice, end to end
About this document: A single-page commercial invoice from A.E. Blake Sales, a Canadian industrial supplier, billed to Nelson Industrial Fabricators. Three line items of abrasive belts and graphite canvas, a customer PO reference, order and ship dates, and a totals block ending at $3,099.67 CAD. The headings are bilingual: "Invoice - Facture", "Vendu à - Sold To".
Processing objective: The objective is to capture who billed whom, for how much, and which goods were supplied. The line item is the middle row of three, chosen because its description carries dimensions, a pack quantity and a tolerance in one string.
Demonstration fields: Invoice number, Supplier, Sold to, Line item description, Total due
The document
1 page
Page 1shown below
Where each value came from
invoice_info.invoice_number
{
"value": "138277",
"page": 1,
"range": {
"end": 224,
"start": 214
},
"box": {
"xmin": 0.6374,
"ymin": 0.09656,
"xmax": 0.761,
"ymax": 0.1111
}
}company_info.supplier_name
{
"value": "A.E. Blake Sales Ltd.",
"page": 1,
"range": {
"end": 82,
"start": 61
},
"box": {
"xmin": 0.55401,
"ymin": 0.02066,
"xmax": 0.68072,
"ymax": 0.03196
}
}customer_info.sold_to_name
{
"value": "NELSON INDUSTRIAL FABRICATORS",
"page": 1,
"range": {
"end": 291,
"start": 262
},
"box": {
"xmin": 0.14236,
"ymin": 0.15809,
"xmax": 0.41357,
"ymax": 0.17021
}
}line_items[1].description
{
"value": "3M 777F RBC Belt 6\"x202\" 60YF 10belts/case (±10%)",
"page": 1,
"range": {
"end": 1447,
"start": 1395
},
"box": {
"xmin": 0.22401,
"ymin": 0.44898,
"xmax": 0.53445,
"ymax": 0.50492
}
}totals_summary.total_due
{
"value": 3099.67,
"page": 1,
"range": {
"end": 2054,
"start": 2040
},
"box": {
"xmin": 0.84299,
"ymin": 0.88372,
"xmax": 0.9256,
"ymax": 0.92477
}
}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.
