Extracting data from business registrations
Each US state's Secretary of State registers businesses on its own forms, from articles of incorporation to certificates of organization for LLCs. Banks, lenders and payment providers often request one when onboarding a business customer, as a PDF from the state's online register or a scan of the filed copy.
Business verification needs the legal name, the entity type, the state of formation, the filing number and the filing date. A know-your-business review can check them against the state register before an account opens or a loan is approved.
What makes business registrations hard
Every state has its own form
Each Secretary of State designs its own filing, and an LLC forms under articles of organization in one state and a certificate in another.
Stamps carry the filing facts
The filing date and the state's acceptance often appear only in a rubber stamp, faint and partly broken on the scan.
Typing and handwriting mixed
Typed answers sit under numbered questions, while signatures and the state's own filing number are often written by hand.
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 business registration, end to end
About this document: A Certificate of Organization for an Idaho limited liability company, filed with the Idaho Secretary of State and served from the state's public business register. One portrait page, an image-only scan. It shows the state's preprinted form filled in by typewriter, a rubber filing stamp, a cashier's register imprint and a handwritten filing number. Page 1 is featured.
Processing objective: The objective is to confirm what the state registered. The business name and entity type come from the typed form, the state from the rubber stamp and the filing number from handwriting in the state-use box. Each value grounds to the mark that carries it.
Demonstration fields: Business name, Entity type, Filing state (stamp), Filing number
The document
1 page
Page 1shown below
Where each value came from
business_name
{
"value": "CAPITAL ASSET REALTY, LLC",
"page": 1,
"range": {
"end": 448,
"start": 423
},
"box": {
"xmin": 0.09242,
"ymin": 0.20323,
"xmax": 0.37123,
"ymax": 0.22297
}
}business_type
{
"value": "Limited Liability Company",
"page": 1,
"range": {
"end": 135,
"start": 107
},
"box": {
"xmin": 0.17736,
"ymin": 0.08398,
"xmax": 0.58969,
"ymax": 0.10741
}
}filing_state_details.state_name
{
"value": "Idaho",
"page": 1,
"range": {
"end": 371,
"start": 357
},
"box": {
"xmin": 0.74455,
"ymin": 0.14295,
"xmax": 0.94872,
"ymax": 0.19267
}
}filing_number
{
"value": "W199421",
"page": 1,
"range": {
"end": 1708,
"start": 1701
},
"box": {
"xmin": 0.63946,
"ymin": 0.91872,
"xmax": 0.84688,
"ymax": 0.9589
}
}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.
