Extracting data from UCC lien searches
Secretary of State offices and commercial search vendors return UCC lien searches in their own report formats. Commercial lenders, equipment financiers and factors order one for every business borrower, receiving the results as a PDF report or a state search certificate.
Credit review needs each financing statement's debtor, secured party, filing number, filing date and collateral. Closing checks those against the deal, and requires a termination before funding wherever an existing lien would take first priority.
What makes UCC lien searches hard
Every provider reports differently
Search vendors and state offices each lay out results their own way, from loose label and value blocks to formal search certificates.
One filing, several entries
A single financing statement can appear more than once, under different debtor names or with amendments, and each entry stays separate.
Five years until lapse
A financing statement lapses five years after filing unless continued, so whether a lien is active depends on its filing date and its amendments.
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 UCC lien search, end to end
About this document: MicroBilt's sample UCC search report, published on its own product page. Two portrait pages: a results list of financing statements filed in one state, then the detail record for a single filing. That record lists its debtors, secured party and filing event. Page 2 is featured. Every name and address is specimen data, and document numbers are masked.
Processing objective: The objective is to describe one financing statement from its detail record: what it is, when and where it was filed, and who holds the lien. Each value grounds to its own labelled line, and the filing date comes back in ISO form.
Demonstration fields: Original document number, Original date filed, Filing state, Filing type code, Secured party
The document
2 of 2 pages
Page 1
Page 2shown below
Where each value came from
filing_detail.original_document_number
{
"value": "98-168-XXXX",
"page": 2,
"range": {
"end": 2632,
"start": 2597
},
"box": {
"xmin": 0.15817,
"ymin": 0.4592,
"xmax": 0.42245,
"ymax": 0.47218
}
}filing_detail.original_date_filed
Printed on the page as Original Date Filed: 06/17/1998, normalized on extraction.
{
"value": "1998-06-17",
"page": 2,
"range": {
"end": 2665,
"start": 2633
},
"box": {
"xmin": 0.52138,
"ymin": 0.45925,
"xmax": 0.79125,
"ymax": 0.47213
}
}filing_detail.filing_state_name
{
"value": "Washington",
"page": 2,
"range": {
"end": 2714,
"start": 2684
},
"box": {
"xmin": 0.52166,
"ymin": 0.47244,
"xmax": 0.78949,
"ymax": 0.48583
}
}filing_detail.events[0].filing_type_code
{
"value": "0801",
"page": 2,
"range": {
"end": 3559,
"start": 3536
},
"box": {
"xmin": 0.52191,
"ymin": 0.78728,
"xmax": 0.74592,
"ymax": 0.79984
}
}filing_detail.secured_parties[0].name
{
"value": "ANY COMPANY",
"page": 2,
"range": {
"end": 3342,
"start": 3331
},
"box": {
"xmin": 0.15927,
"ymin": 0.7096,
"xmax": 0.26123,
"ymax": 0.72747
}
}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.
