Extracting data from Schedule E forms
Individuals reporting rental real estate income on Schedule E attach it to Form 1040, using an IRS layout with three property columns. Lenders may request returns as PDFs or scans when applicants use rental income to qualify; the required history varies by loan program.
Underwriting needs each property's rents, expenses, depreciation, mortgage interest and net income. A rental income worksheet such as Fannie Mae Form 1038 adds the noncash and financing costs back to arrive at qualifying rental income.
What makes Schedule E forms hard
Three property columns
Amounts sit in property columns A to C beside one shared list of labels, so each value belongs to a row and a column.
Totals repeat below
Rents and net income or loss carry down into the summary lines at the foot of the page, beside the property columns.
Add-backs scattered by line
The expenses a lender adds back, such as depreciation, mortgage interest and taxes, sit on separate lines among fifteen expense rows.
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 E, end to end
About this document: Page 1 of a completed Schedule E for a single-family rental, from a mortgage insurer's lender training course on calculating rental income. One portrait page: Part I with a full year of rents and expenses in property column A, and the summary block below. Page 1 is featured. The filer and property are teaching placeholders.
Processing objective: The objective is to read the figures a rental income calculation starts from: what the property took in and the expenses a lender adds back. Those add-backs return to the net rental income printed at the foot of the column.
Demonstration fields: Rents received (line 3), Mortgage interest (line 12), Taxes (line 16), Depreciation (line 18), Net rental income (line 21)
The document
1 page
Page 1shown below
Where each value came from
properties[0].rents_received
{
"value": 73900,
"page": 1,
"range": {
"end": 2174,
"start": 2167
},
"box": {
"xmin": 0.51796,
"ymin": 0.39393,
"xmax": 0.6591,
"ymax": 0.40908
}
}properties[0].expenses.mortgage_interest
{
"value": 19332,
"page": 1,
"range": {
"end": 3450,
"start": 3443
},
"box": {
"xmin": 0.51792,
"ymin": 0.54532,
"xmax": 0.65911,
"ymax": 0.5607
}
}properties[0].expenses.taxes
{
"value": 10344,
"page": 1,
"range": {
"end": 3929,
"start": 3922
},
"box": {
"xmin": 0.5179,
"ymin": 0.60603,
"xmax": 0.65912,
"ymax": 0.62114
}
}properties[0].expenses.depreciation_or_depletion
{
"value": 3661,
"page": 1,
"range": {
"end": 4193,
"start": 4187
},
"box": {
"xmin": 0.51789,
"ymin": 0.63618,
"xmax": 0.65912,
"ymax": 0.65153
}
}properties[0].income_or_loss
{
"value": 31185,
"page": 1,
"range": {
"end": 4731,
"start": 4724
},
"box": {
"xmin": 0.51786,
"ymin": 0.68178,
"xmax": 0.65913,
"ymax": 0.72717
}
}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.
