Extracting data from good standing certificates
Good standing certificates come from each state's business filing office. Each state titles and words its own: a certificate of existence in some, a certificate of status in others. Lenders and acquirers request one for each entity in a deal, dated within weeks of closing, as a PDF downloaded from the state's website.
Closing counsel needs the entity name, the state ID number, the issue date and the confirmation number. The closing checklist records each certificate against its entity and checks that the issue date falls inside the window the credit agreement allows.
What makes certificates of good standing hard
Values sit inside sentences
Most states fill the entity name, formation date and ID number into blanks in a certifying paragraph, so each value is identified by its sentence.
Several dates on one page
A certificate can print a formation date, a records-current-through date and an issue date, often in the same format on adjacent lines.
Each state names it differently
One state issues a certificate of existence, another a certificate of fact of good standing, each with its own wording and order of facts.
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 certificate of good standing, end to end
About this document: A Certificate of Fact of Good Standing from the Colorado Secretary of State, one portrait page issued electronically. It certifies a nonprofit corporation, the Colorado State Science Fair, with each value filled into a blank in the certificate's sentences. The page also carries the state seal, the Secretary's facsimile signature and a notice on validating the certificate online. Page 1 is featured.
Processing objective: The objective is to confirm which entity the state vouches for, since when and on what date it said so. The page prints three similar dates. Two say how current the state's records are, and only the third is the date the certificate was issued.
Demonstration fields: Entity name, Formation date, Entity ID number, Issue date, Confirmation number
The document
1 page
Page 1shown below
Where each value came from
entity.name
{
"value": "COLORADO STATE SCIENCE FAIR, INC.",
"page": 1,
"range": {
"end": 266,
"start": 233
},
"box": {
"xmin": 0.33365,
"ymin": 0.2542,
"xmax": 0.66773,
"ymax": 0.26833
}
}entity.formation_date
{
"value": "02/24/1977",
"page": 1,
"range": {
"end": 390,
"start": 296
},
"box": {
"xmin": 0.1137,
"ymin": 0.32888,
"xmax": 0.8866,
"ymax": 0.34573
}
}entity.entity_id_number
{
"value": "19871318213",
"page": 1,
"range": {
"end": 534,
"start": 499
},
"box": {
"xmin": 0.11544,
"ymin": 0.36111,
"xmax": 0.39292,
"ymax": 0.37689
}
}issuance.issue_date
{
"value": "01/23/2026",
"page": 1,
"range": {
"end": 982,
"start": 882
},
"box": {
"xmin": 0.11409,
"ymin": 0.47281,
"xmax": 0.88699,
"ymax": 0.48928
}
}issuance.confirmation_number
{
"value": "18120661",
"page": 1,
"range": {
"end": 1040,
"start": 983
},
"box": {
"xmin": 0.11519,
"ymin": 0.48896,
"xmax": 0.55588,
"ymax": 0.50553
}
}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.
