Turn court filings and public records into structured, searchable data

Case numbers, parties, recording information, legal descriptions, dates, and fees remain scattered across filed documents until someone extracts them. Nutrient Data Extraction API turns court filings, deeds, and clerk records into structured data — with confidence scores and source context so staff can review uncertain values, not every field.

Court filing document with case details and party information alongside extracted structured JSON output

Trusted by enterprises, governments, and teams building document workflows at scale

Used by Lufthansa, Disney, Autodesk, UBS, Dropbox, IBM
Lufthansa
Disney
Autodesk
UBS
Dropbox
IBM

USE CASES

Example court and public record workflows

Court filing intake extraction

Court filing intake

Extract case numbers, filing types, parties, attorneys, judges, and hearing dates from civil, criminal, and administrative filings.

Recording and land records extraction

Recording and land records

Structure instrument types, recording numbers, grantor and grantee details, parcel identifiers, and legal descriptions from deeds and recorded instruments.

Clerk administrative records extraction

Clerk and administrative records

Extract document type, applicant, fees, reference numbers, submission dates, and status information from clerk-issued records.

Document indexing and classification

Document indexing and classification

Turn document content into structured metadata for search, classification, retrieval, and records management systems.

Records routing and case management

Records routing and case management

Export typed JSON that maps to the fields case management, recording, or enterprise content platforms expect.

GOVERNED EXTRACTION

Why not rely on LLM-only extraction for public records?

LLMs can interpret a court filing — but public record workflows need deterministic, traceable output grounded in the source document, not generated answers that vary between runs.

Predictable structured output

Typed output remains tied to the source document — not generated text that changes from one run to the next.

Confidence signals for routing and review

Flag uncertain values before they move downstream into case management or recording systems.

Coordinates and page references

Every extracted value is anchored to its source location for traceability and staff review.

Layout-aware structure

Tables, key-value regions, and reading order preserved — not flattened into unstructured text.

Human review before indexing

Support validation steps before structured data enters the official record or downstream system.

Auditability for public record workflows

Source context and page detail support traceable, reviewable government document workflows.

WHAT YOU CAN EXTRACT

Structured fields from any court or public record

Structured data extracted from a court filing document
Case identifiers and filing details

Case numbers, court, jurisdiction, filing type, filing date, and hearing dates from civil, criminal, and administrative filings.


Parties and representatives

Plaintiff, defendant, attorney, agency, and contact details from court filings and administrative records.


Recording information

Instrument type, recording number, recording date, and book-and-page references from deeds and recorded instruments.


Property and legal descriptions

Parcel number, property address, legal description, grantor, and grantee from land and recording records.


Monetary values and fees

Consideration amounts, filing fees, and other financial values from court filings and recorded instruments.


Handwritten and mixed-format fields

Stamps, handwritten annotations, notary information, and signature presence from older or scanned records.


HOW IT WORKS

From public record to structured output

Parse

Turn court filings, deeds, and scanned public records into document structure.

Extract

Identify case details, parties, recording information, legal descriptions, and document metadata.

Map

Define the fields the workflow needs using the schema generator in Studio, or write a JSON Schema directly. Get back structured, validated output.

Structure

Return typed JSON for records systems and validation, or Markdown for search and AI workflows.

Process

Send structured data into court management, recording, records management, or public access systems.

OUTPUT FORMATS

Spatial JSON. Or Markdown. From the same API.

Confidence scores, coordinates, and page context included.
Choose output: "json" or Markdown per request.

Spatial JSON

For extraction · validation · review

.json
{
"type": "keyValueRegion",
"id": "kv_c1d2e3",
"bounds": { "x": 82, "y": 128, "width": 340, "height": 96 },
"confidence": 0.98,
"page": { "pageIndex": 0, "pageNumber": 1 },
"pairs": [
{
"key": { "entityType": "QUESTION", "value": "Case number",
"bounds": { "x": 82, "y": 128, "width": 100, "height": 24 },
"confidence": 0.99 },
"value": { "entityType": "ANSWER", "value": "2024-CV-008841",
"bounds": { "x": 190, "y": 128, "width": 150, "height": 24 },
"confidence": 0.99 },
"relationshipConfidence": 0.97
},
{
"key": { "entityType": "QUESTION", "value": "Filing type",
"bounds": { "x": 82, "y": 164, "width": 100, "height": 24 },
"confidence": 0.98 },
"value": { "entityType": "ANSWER", "value": "Civil Complaint",
"bounds": { "x": 190, "y": 164, "width": 130, "height": 24 },
"confidence": 0.98 },
"relationshipConfidence": 0.96
},
{
"key": { "entityType": "QUESTION", "value": "Filing date",
"bounds": { "x": 82, "y": 200, "width": 100, "height": 24 },
"confidence": 0.99 },
"value": { "entityType": "ANSWER", "value": "2024-03-15",
"bounds": { "x": 190, "y": 200, "width": 100, "height": 24 },
"confidence": 0.99 },
"relationshipConfidence": 0.97
}
]
}

Markdown

For RAG · search · knowledge bases

.md
# Court Filing — Civil Complaint
**Case number** 2024-CV-008841
**Court** Superior Court, Los Angeles County
**Filing date** March 15, 2024
## Parties
| Role | Name |
| --- | --- |
| Plaintiff | Riverside Capital LLC |
| Defendant | Oakwood Properties Inc |
**Judge** Hon. Patricia Vega
**Filing type** Civil Complaint

Regional processing options

Choose supported processing regions for government and enterprise deployments.

SOC 2 Type 2 audited

Audited annually. Reports available under NDA for enterprise customers.

Trust and compliance

Built for government and public record workflows in production

TLS encryption by default

All API communication is encrypted. Unencrypted requests are rejected.

Court and public record extraction questions

Can the API extract handwriting and stamps from older filings?

Yes. For handwritten fields, stamps, and mixed-format documents, the API applies intelligent character recognition to capture what standard OCR misses. Every extracted value includes a confidence score so uncertain fields can be flagged for staff review before moving downstream.

What file formats are supported?

Data Extraction API processes PDFs; images (including scans and photos); and Word, Excel, and PowerPoint files. It handles scanned court documents, image-based filings, and mixed digital/image records without requiring a separate OCR pipeline.

Is this a court management or records management system?

Nutrient Data Extraction API is an extraction layer, not a court management, recording, or records management platform. It turns document content into structured data so that data can be reviewed, validated, and routed into the systems organizations and software providers already use.

How do I validate extracted data before it enters downstream systems?

Every extracted element includes confidence scores, page references, and coordinates so teams can flag low-confidence fields for review, trace values back to the source document, and validate results before they enter case management, recording, or public access systems.

How do I define the fields to extract from court records?

Use the schema generator in Studio — upload example filings, deeds, or clerk documents and describe the document type. It generates a JSON Schema for the /extract endpoint. Fields like case number, parties, recording information, and legal descriptions can also be defined manually. Refer to the documentation for supported field types and limits.

When should I use agentic mode for court documents?

Use agentic mode for degraded scans, older handwritten filings, and documents with complex visual layouts where understand mode produces insufficient results. Agentic mode adds a vision language model (VLM) on top of the understand pipeline for complex visual content. It costs 18 credits per page.

GET STARTED

Start extracting data from court and public records

5,000 free credits per month — no credit card required.

Free account includes:

    • 5,000 Data Extraction API credits per month
    • Parse PDFs, scans, images, and Office files
    • Structured JSON output with confidence scores and source context
    • SOC 2 Type 2 audited