Extracting data from auto lease agreements
Dealers sign each vehicle lease on a form set by the lessor and the state, so every captive finance company and bank prints its own version. The lessor's funding team reviews every contract its dealer network writes, delivered as an e-contract or scanned paper, before paying the dealer.
Funding needs the gross and adjusted capitalized cost, the residual value, the rent charge, the term and the monthly payment. A lease origination system checks that arithmetic against the approved deal, then books the payment schedule and residual for servicing.
What makes auto lease agreements hard
The payment is a worked calculation
Federal rules require the lease to show how the monthly payment is derived, as a column of lines joined by arithmetic operators.
One payment, printed many times
The monthly payment appears in the amount due at signing, the payment schedule and the calculation total, each a separate federal disclosure.
Terms typed into blanks
The mileage allowance and the per-mile overage charge are typed into blanks inside numbered paragraphs, among dense legal-size terms.
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 auto lease agreement, end to end
About this document: A closed-end motor vehicle lease for a new Honda, written by a Florida dealer on the Reynolds and Reynolds form Honda Financial Services uses in that state. Five legal-size portrait pages open with the federal lease disclosures and payment calculation, followed by itemized costs, two pages of terms, and the arbitration clause with signatures. Page 1 is featured. Personal details and signatures were replaced before publication.
Processing objective: The objective is to trace the lease from the vehicle's capitalized cost to the monthly payment, with each figure tied to its own line of the calculation. The lines reconcile: a gross capitalized cost of 28,539.00 less a 101.29 reduction leaves 28,437.71, and the residual value comes off that next.
Demonstration fields: Gross capitalized cost, Capitalized cost reduction, Adjusted capitalized cost, Residual value, Total monthly payment
The document
4 of 5 pages
Page 1shown below
Page 2
Page 3
Page 4
Where each value came from
payment_calculation.gross_capitalized_cost
{
"value": 28539,
"page": 1,
"range": {
"end": 5566,
"start": 5555
},
"box": {
"xmin": 0.79483,
"ymin": 0.64944,
"xmax": 0.9628,
"ymax": 0.67251
}
}payment_calculation.capitalized_cost_reduction
{
"value": 101.29,
"page": 1,
"range": {
"end": 5757,
"start": 5747
},
"box": {
"xmin": 0.79423,
"ymin": 0.67249,
"xmax": 0.96295,
"ymax": 0.69679
}
}payment_calculation.adjusted_capitalized_cost
{
"value": 28437.71,
"page": 1,
"range": {
"end": 5887,
"start": 5874
},
"box": {
"xmin": 0.79394,
"ymin": 0.69672,
"xmax": 0.96302,
"ymax": 0.70868
}
}payment_calculation.residual_value
{
"value": 18070,
"page": 1,
"range": {
"end": 6044,
"start": 6031
},
"box": {
"xmin": 0.79366,
"ymin": 0.70862,
"xmax": 0.96309,
"ymax": 0.72036
}
}payment_calculation.total_scheduled_payment
{
"value": 435.04,
"page": 1,
"range": {
"end": 6908,
"start": 6898
},
"box": {
"xmin": 0.79074,
"ymin": 0.82478,
"xmax": 0.96383,
"ymax": 0.83954
}
}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. VPC and on-prem deployment require an Enterprise plan.
