Extracting data from alimony court orders
A family court orders spousal support in a judgment or a support order, on the state's own judicial forms. Mortgage lenders collect one from every applicant who receives or pays alimony, as a scanned certified copy uploaded to the borrower portal.
Underwriting needs the payor, the support type, the monthly amount, the start date and any end date. The loan origination system counts the payment as income only when it continues for three more years, and counts it as a debt when the borrower pays.
What makes alimony court orders hard
Support set by checkboxes
Who pays whom, and whether support is spousal or family, are ticked boxes inside one sentence that runs across several lines of the form.
Terms split across two forms
A judgment often sets support as described in an attached order, so the amount and dates sit on a separate form incorporated by reference.
Certified copies are scans
The copy a borrower provides is usually a scan of a certified court record, often black and white and slightly skewed on the glass.
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 alimony court order, end to end
About this document: A California stipulated judgment of dissolution and the spousal support order attachment it incorporates, from a court self-help center's sample packet. Four scanned portrait pages: the judgment on pages 1 and 2, the support order on pages 3 and 4. Page 3 is featured. Every party is a specimen name.
Processing objective: The objective is to read the support order itself. It names the case, who pays, what kind of support and how much each month, after how long a marriage. Each answer comes from a ticked box or a typed blank, grounded to its own line.
Demonstration fields: Case number, Paid by, Support type, Monthly amount, Length of marriage (years)
The document
4 of 4 pages
Page 1
Page 2
Page 3shown below
Page 4
Where each value came from
case_number
{
"value": "FL110572",
"page": 3,
"range": {
"end": 7682,
"start": 7674
},
"box": {
"xmin": 0.63527,
"ymin": 0.08555,
"xmax": 0.91801,
"ymax": 0.10682
}
}support_order.payor
{
"value": "respondent",
"page": 3,
"range": {
"end": 9595,
"start": 9563
},
"box": {
"xmin": 0.03268,
"ymin": 0.60281,
"xmax": 0.72326,
"ymax": 0.62497
}
}support_order.support_type
{
"value": "spousal support",
"page": 3,
"range": {
"end": 9670,
"start": 9649
},
"box": {
"xmin": 0.07872,
"ymin": 0.61751,
"xmax": 0.67074,
"ymax": 0.64013
}
}support_order.monthly_amount
{
"value": 407,
"page": 3,
"range": {
"end": 9756,
"start": 9713
},
"box": {
"xmin": 0.07723,
"ymin": 0.63212,
"xmax": 0.87437,
"ymax": 0.65916
}
}support_order.marriage_length_years
{
"value": 15,
"page": 3,
"range": {
"end": 8895,
"start": 8814
},
"box": {
"xmin": 0.06355,
"ymin": 0.36901,
"xmax": 0.63513,
"ymax": 0.39209
}
}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.
