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

Extracting data from writs of execution

A court clerk issues a writ of execution at the judgment creditor's request, on a state checkbox form or as an order drafted in prose. The sheriff's civil unit receives one for every judgment it enforces by sale, filed on paper or sent as a scanned PDF by the creditor's attorney.

The sheriff needs the case number, the amount to satisfy, the post-judgment rate and per diem, and the property. Those feed the sheriff's sale process, which schedules the sale, publishes notice and computes the amount due on the day of sale.

Page 2 of a sample Writ of Execution, with extracted values outlined
2,966Markdown characters
20parse blocks
24fields extracted
The problem

What makes writs of execution hard

Checkbox forms and drafted orders

California's EJ-130 sets the writ's type with checkboxes at the top, while other courts issue a writ drafted in prose by the creditor's attorney.

The money sits in sentences

On a drafted writ, the sum, the date it is stated as of, the post-judgment rate and the daily interest can share two sentences.

A deadline set by statute

A writ has to be returned within a fixed period, 180 days on California's form, so the deadline has to be read from the order.

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 writ of execution, end to end

About this document: A writ of execution on real property issued by the Multnomah County Circuit Court in Oregon, heading a sheriff's sale packet. Two scanned portrait pages on line-numbered pleading paper: the caption and the order on page 1, then the money, the creditor and the sealed signature on page 2. Page 2 is featured. The defendants, property and file numbers were replaced with stand-ins.

Processing objective: The objective is to read what the sheriff is ordered to collect, and for whom. The sum and its daily interest are stated inside one sentence. The creditor is named in its own sentence below, and each value grounds to the pleading line that prints it.

Demonstration fields: Amount to satisfy, Per-diem interest, Property, Judgment creditor

The document

2 of 2 pages
  • Page 1 of the sample Writ of ExecutionPage 1
  • Page 2 of the sample Writ of ExecutionPage 2shown below

Where each value came from

Page 2 of the sample Writ of Execution, with every featured field outlined
Amount to satisfyamount_to_satisfy
450,797.72
The region of the sample Writ of Execution containing Amount to satisfy, with the extracted value outlined
extraction_metadata["amount_to_satisfy"]
{
  "value": 450797.72,
  "page": 2,
  "range": {
    "end": 1820,
    "start": 1726
  },
  "box": {
    "xmin": 0.11344,
    "ymin": 0.14907,
    "xmax": 0.88742,
    "ymax": 0.17324
  }
}
Per-diem interestper_diem_interest
110.96
The region of the sample Writ of Execution containing Per-diem interest, with the extracted value outlined
extraction_metadata["per_diem_interest"]
{
  "value": 110.96,
  "page": 2,
  "range": {
    "end": 1916,
    "start": 1821
  },
  "box": {
    "xmin": 0.1142,
    "ymin": 0.18541,
    "xmax": 0.88915,
    "ymax": 0.20806
  }
}
Propertyproperty_address
100 Sample Avenue, Portland, OR 97000
The region of the sample Writ of Execution containing Property, with the extracted value outlined
extraction_metadata["property_address"]
{
  "value": "100 Sample Avenue, Portland, OR 97000",
  "page": 2,
  "range": {
    "end": 1725,
    "start": 1644
  },
  "box": {
    "xmin": 0.11325,
    "ymin": 0.11253,
    "xmax": 0.88796,
    "ymax": 0.13759
  }
}
Judgment creditorjudgment_creditor
PennyMac Loan Services, LLC
The region of the sample Writ of Execution containing Judgment creditor, with the extracted value outlined
extraction_metadata["judgment_creditor"]
{
  "value": "PennyMac Loan Services, LLC",
  "page": 2,
  "range": {
    "end": 2032,
    "start": 1948
  },
  "box": {
    "xmin": 0.17226,
    "ymin": 0.25667,
    "xmax": 0.86779,
    "ymax": 0.2773
  }
}

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

Writ of Execution processing highlights

Amount to satisfy
Post-judgment interest rate
Per-diem interest
As-of dates normalized
Return deadline in days
Property and legal description
Judgment creditor and debtors
Case number and court
Court seal and signature
Handwritten issue dates
Line-numbered pleading paper
Bounding box for every value
FAQs

Questions, answered

Yes. Describe each amount in your schema, such as the sum to satisfy and the daily interest. Extraction reads them out of the prose as separate numbers, and each grounds to the line that states it.

Yes. Parsing writes every checkbox into the Markdown in one standard form, marked checked or unchecked beside its label. Define the writ type as a field and the checked option comes back as its value.

Yes. Parsing marks seals, stamps and signatures as attestation blocks, labelled STAMPED or SIGNED in the Markdown. A boolean field can read those labels, and its grounding points at the seal on the page.

No. A schema names the fields you want and describes them in plain language. Extraction reads the parsed writ for meaning, so one schema covers each state's form and each attorney's drafting.

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

Start extracting writ of execution data

Reliable, structured outputs with full traceability in minutes