Take a live AI-guided product tour with Lando.Launch AI demo
Document type

Extracting data from articles of incorporation

Each state sets its own requirements, so articles of incorporation range from a one-page state form to a charter drafted by counsel. Delaware calls the filing a certificate of incorporation. Investors and acquirers collect one for every entity in a corporate group, as certified state copies or as scans in a data room.

Diligence needs the legal name, the state filing number, the registered agent and each authorized share class with its par value. Deal counsel reconciles the share counts against the capitalization table, confirming that issued stock stays within what the charter authorizes.

Page 1 of a sample Articles of Incorporation, with extracted values outlined
5,646Markdown characters
34parse blocks
27fields extracted
The problem

What makes articles of incorporation hard

Every state sets its own format

One state generates articles from an online questionnaire, while a Delaware certificate of incorporation is drafted by counsel and can run to pages of prose.

Capital terms are written as articles

Share classes and par values sit in a numbered article, and a venture-backed charter can spend pages on preferred stock liquidation and conversion terms.

Amendments change the current terms

A corporation amends its articles to add shares or change its name, so the current terms can span the original filing and certificates of amendment.

How it works

Parse, extract, verify

1

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.

2

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.

3

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.

Worked example

One articles of incorporation, end to end

About this document: Profit corporation articles of incorporation for Top Tier Sports (USA) Inc., generated and filed by the Wyoming Secretary of State, four portrait pages. The company filed them with the SEC as an exhibit to a crowdfunding offering statement. Page 1 carries the articles, page 2 the filer's checkbox attestations and page 3 the registered agent's consent. Page 4 is the state's certificate of incorporation. Page 1 is featured.

Processing objective: The objective is to record what the state filed: the number it assigned, the corporation it formed and the agent that accepts service. The capital it may issue sits in two share counts beside their par values, with common stock authorized as "Unlimited".

Demonstration fields: Original ID, Corporation name, Registered agent, Common shares authorized, Preferred shares authorized

The document

4 of 4 pages
  • Page 1 of the sample Articles of IncorporationPage 1shown below
  • Page 2 of the sample Articles of IncorporationPage 2
  • Page 3 of the sample Articles of IncorporationPage 3
  • Page 4 of the sample Articles of IncorporationPage 4

Where each value came from

Page 1 of the sample Articles of Incorporation, with every featured field outlined
Original IDfiling.filing_id
2024-001549080
The region of the sample Articles of Incorporation containing Original ID, with the extracted value outlined
extraction_metadata["filing.filing_id"]
{
  "value": "2024-001549080",
  "page": 1,
  "range": {
    "end": 229,
    "start": 202
  },
  "box": {
    "xmin": 0.52629,
    "ymin": 0.08269,
    "xmax": 0.74926,
    "ymax": 0.0988
  }
}
Corporation namecorporation_name
Top Tier Sports (USA) Inc.
The region of the sample Articles of Incorporation containing Corporation name, with the extracted value outlined
extraction_metadata["corporation_name"]
{
  "value": "Top Tier Sports (USA) Inc.",
  "page": 1,
  "range": {
    "end": 346,
    "start": 320
  },
  "box": {
    "xmin": 0.11057,
    "ymin": 0.23869,
    "xmax": 0.30984,
    "ymax": 0.25582
  }
}
Registered agentregistered_agent.name
Cloud Peak Law, LLC
The region of the sample Articles of Incorporation containing Registered agent, with the extracted value outlined
extraction_metadata["registered_agent.name"]
{
  "value": "Cloud Peak Law, LLC",
  "page": 1,
  "range": {
    "end": 454,
    "start": 435
  },
  "box": {
    "xmin": 0.11043,
    "ymin": 0.29289,
    "xmax": 0.27565,
    "ymax": 0.30886
  }
}
Common shares authorizedauthorized_shares[0].number_of_shares
Unlimited
The region of the sample Articles of Incorporation containing Common shares authorized, with the extracted value outlined
extraction_metadata["authorized_shares[0].number_of_shares"]
{
  "value": "Unlimited",
  "page": 1,
  "range": {
    "end": 866,
    "start": 832
  },
  "box": {
    "xmin": 0.11029,
    "ymin": 0.50026,
    "xmax": 0.412,
    "ymax": 0.51614
  }
}
Preferred shares authorizedauthorized_shares[1].number_of_shares
110,000
The region of the sample Articles of Incorporation containing Preferred shares authorized, with the extracted value outlined
extraction_metadata["authorized_shares[1].number_of_shares"]
{
  "value": "110,000",
  "page": 1,
  "range": {
    "end": 902,
    "start": 867
  },
  "box": {
    "xmin": 0.11007,
    "ymin": 0.51833,
    "xmax": 0.40343,
    "ymax": 0.53472
  }
}

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
Why LandingAI?

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.

Compare plans
Capabilities

Articles of Incorporation processing highlights

State filing numbers and stamps
Authorized shares by class
Par value per class
Non-numeric share authorizations
Registered agent details
Principal and mailing addresses
Incorporator signature blocks
Checkbox attestations
Seals and signatures labeled
Amended and restated charters
Native PDFs and scans
Bounding box for every value
FAQs

Questions, answered

Yes. Define the share count as a string field. A count printed as a word comes back as written, grounded to its own line beside the numeric counts of the other classes.

Yes. Define the share classes as an array of objects, and each class comes back with its own count and par value paired. Where the two print side by side, each value grounds to its own column.

Yes. Parsing renders a ticked box as [x] and an empty one as [ ], so each attestation reads plainly in the Markdown. Signature and seal blocks come back as attestations, labeled SIGNED or SEALED.

No. A schema describes each field in plain language, and x-alternativeNames lists the labels states print for it, such as Original ID or File Number. Property order is independent of the page, so one schema covers each state's layout.

Every extracted value carries the character ranges it was quoted from in the parsed Markdown. The Ground API maps those ranges to a page and a bounding box, so a reviewer sees the line of the filing that printed each value.

Start extracting articles of incorporation data

Reliable, structured outputs with full traceability in minutes