*** September 2026 Major Release ***Read and watch
Document type

Extracting data from wire instructions

Title companies, law firms and loan servicers each print wire instructions on their own letterhead. A closing team receives one from every party it pays at a real estate closing, including the seller and each lender being paid off. They arrive as PDF attachments by email or through a closing portal.

Escrow needs the receiving bank, the routing number, the account number, the account name and the reference to quote. Those go into the bank's outgoing wire system once a callback to a number already on file confirms them.

Page 1 of a sample Wire Instructions, with extracted values outlined
971Markdown characters
8parse blocks
15fields extracted
The problem

What makes wire instructions hard

Forged copies look genuine

Before funds are wired, business email compromise sends a copy on the same letterhead with only the bank and account changed.

Each payee writes its own labels

The same field reads Bank Account on one payee's page and Beneficiary Account No. on the next, each in its own layout.

Lookalike numbers stacked together

Routing, account and reference numbers sit a line apart as similar strings of digits, and each one belongs in its own field.

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 wire instruction example, end to end

About this document: First Integrity Title Company's wire instructions for closing funds, one portrait page split from a preliminary title report. A letterhead and the terms for sending funds sit above the instruction block, which runs from the receiving bank to the property address. Page 1 is featured. The account, routing and order numbers and the property address were replaced with stand-ins.

Processing objective: The objective is to capture the full payment route, from the bank that receives the wire to the reference the sender quotes. Each value is grounded together with its printed label, which is the pairing a reviewer checks against a known-good copy before any money moves.

Demonstration fields: Receiving bank, ABA routing number, Account number, Account name, Reference order number

The document

1 page
  • Page 1 of the sample Wire InstructionsPage 1shown below

Where each value came from

Page 1 of the sample Wire Instructions, with every featured field outlined
Receiving bankreceiving_bank.name
First Western Trust Bank
The region of the sample Wire Instructions containing Receiving bank, with the extracted value outlined
extraction_metadata["receiving_bank.name"]
{
  "value": "First Western Trust Bank",
  "page": 1,
  "range": {
    "end": 595,
    "start": 562
  },
  "box": {
    "xmin": 0.17283,
    "ymin": 0.316,
    "xmax": 0.60921,
    "ymax": 0.33066
  }
}
ABA routing numberaba_routing_number
796630226
The region of the sample Wire Instructions containing ABA routing number, with the extracted value outlined
extraction_metadata["aba_routing_number"]
{
  "value": "796630226",
  "page": 1,
  "range": {
    "end": 691,
    "start": 665
  },
  "box": {
    "xmin": 0.17214,
    "ymin": 0.39,
    "xmax": 0.49653,
    "ymax": 0.40841
  }
}
Account numberaccount_number
6677087
The region of the sample Wire Instructions containing Account number, with the extracted value outlined
extraction_metadata["account_number"]
{
  "value": "6677087",
  "page": 1,
  "range": {
    "end": 713,
    "start": 692
  },
  "box": {
    "xmin": 0.173,
    "ymin": 0.41992,
    "xmax": 0.47848,
    "ymax": 0.43819
  }
}
Account nameaccount_name
First Integrity Title Company, a California Corporation - California IOLTA Account
The region of the sample Wire Instructions containing Account name, with the extracted value outlined
extraction_metadata["account_name"]
{
  "value": "First Integrity Title Company, a California Corporation - California IOLTA Account",
  "page": 1,
  "range": {
    "end": 810,
    "start": 714
  },
  "box": {
    "xmin": 0.17294,
    "ymin": 0.45001,
    "xmax": 0.92103,
    "ymax": 0.48177
  }
}
Reference order numberreference_number
FIN-78796415
The region of the sample Wire Instructions containing Reference order number, with the extracted value outlined
extraction_metadata["reference_number"]
{
  "value": "FIN-78796415",
  "page": 1,
  "range": {
    "end": 844,
    "start": 811
  },
  "box": {
    "xmin": 0.1724,
    "ymin": 0.49521,
    "xmax": 0.52099,
    "ymax": 0.51225
  }
}

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.

Compare plans
Capabilities

Wire Instructions processing highlights

No per-payee templates
ABA routing numbers
Account numbers and names
Receiving bank and address
Reference and order numbers
IOLTA and trust accounts
Wire-only and ACH terms
Image-only PDFs and scans
Multi-line bank addresses
Label and value together
Bounding box for every value
Zero data retention available
FAQs

Questions, answered

No. A schema names the fields you want and describes them in plain language. Extraction reads the parsed page for meaning, so one schema covers each payee's own labels and layout.

Extract both documents with the same schema and compare them field by field. Every value carries its page and bounding box, so a reviewer sees a changed account number highlighted where it was printed.

Yes. A boolean field such as whether ACH is accepted reads the sentence that states it. Grounding points at that sentence, so the term can be checked alongside the account details.

Yes. Parsing works from the rendered page, so a PDF printed as vector shapes parses the same way as a scan or a native PDF. Every value is grounded to its position on the page.

Accounts are available with zero data retention. Documents are deleted when processing finishes, and results once they are delivered. That sits alongside SOC 2 Type II, GDPR and HIPAA compliance, and a schema can limit extraction to the fields a workflow needs.

Start extracting wire instructions data

Reliable, structured outputs with full traceability in minutes