Extracting data from Schedule C forms
Sole proprietors attach a Schedule C to their 1040 each year, printed by tax software on that year's IRS layout. Mortgage and small business lenders collect two years of them from every self-employed borrower, as PDFs and scans uploaded with the full return.
Underwriting needs gross receipts, total expenses, net profit and the deductions that add back, such as depreciation. A cash flow analysis such as Fannie Mae Form 1084 turns those into the income a borrower qualifies on.
What makes Schedule C forms hard
Expenses in two columns
Part II runs expense lines down two side-by-side columns, each with its own amount column, so every figure belongs to one numbered line.
Receipts repeat down Part I
A business with no returns or cost of goods prints one figure as gross receipts, gross profit and gross income, on separate lines.
Checkboxes and coded boxes
The header sets the accounting method with checkboxes and prints the six-digit business code one digit per box.
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 Schedule C, end to end
About this document: The two pages of Schedule C from an IRS e-file test scenario, published so tax software vendors can check their output. An invented sole proprietor's design business, with income and expenses on page 1 and blank cost of goods and vehicle sections on page 2. Page 1 is featured. Every value is IRS test data.
Processing objective: The objective is to follow the business from its name to its bottom line. Gross receipts carry down to gross income, total expenses come off, and what remains is the net profit. Each figure grounds to its own line's amount cell.
Demonstration fields: Business name (line C), Gross receipts (line 1), Gross income (line 7), Total expenses (line 28), Net profit (line 31)
The document
2 of 2 pages
Page 1shown below
Page 2
Where each value came from
business.business_name
{
"value": "ENERGY BUILD",
"page": 1,
"range": {
"end": 819,
"start": 742
},
"box": {
"xmin": 0.05656,
"ymin": 0.16651,
"xmax": 0.72913,
"ymax": 0.19682
}
}income.line_1_gross_receipts
{
"value": 35235,
"page": 1,
"range": {
"end": 1918,
"start": 1912
},
"box": {
"xmin": 0.77666,
"ymin": 0.31812,
"xmax": 0.94231,
"ymax": 0.34847
}
}income.line_7_gross_income
{
"value": 35235,
"page": 1,
"range": {
"end": 2506,
"start": 2500
},
"box": {
"xmin": 0.77677,
"ymin": 0.42433,
"xmax": 0.94234,
"ymax": 0.43871
}
}expenses.line_28_total_expenses
{
"value": 10907,
"page": 1,
"range": {
"end": 4997,
"start": 4991
},
"box": {
"xmin": 0.77595,
"ymin": 0.69697,
"xmax": 0.94269,
"ymax": 0.71216
}
}line_31_net_profit_or_loss
{
"value": 24328,
"page": 1,
"range": {
"end": 6107,
"start": 6101
},
"box": {
"xmin": 0.77579,
"ymin": 0.83652,
"xmax": 0.94274,
"ymax": 0.84844
}
}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.
