> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sterndesk.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Turn documents into structured, reliable data with the Sterndesk API

# Introduction

<img src="https://cdn.prod.website-files.com/69281b386842bdbd66621ea5/6928346bf5869d1427617e10_Hero%20image%20(1).webp" alt="Sterndesk - Turn documents into structured data" />

Sterndesk is a document processing API that extracts structured data from complex documents. It automates workflows that previously required manual data entry—whether you're processing shipping manifests, research papers, compliance reports, or enterprise records.

## What Sterndesk Does

The API accepts documents via upload or URL crawling and returns structured JSON data according to schemas you define. Key capabilities include:

* **Document classification** — Automatically identify document types
* **Data extraction** — Extract fields, tables, and values using AI
* **Schema-based output** — Define exactly what data you need and how it should be structured
* **Batch processing** — Process thousands of documents in a single request
* **Flexible ingestion** — Feed documents via direct upload, URL crawling, or integrations

## Core Concepts

Sterndesk is organized around four main concepts:

| Concept                                                                 | Description                                                                    |
| ----------------------------------------------------------------------- | ------------------------------------------------------------------------------ |
| [**Organizations & Projects**](/concepts/01-organizations-and-projects) | Logical containers for managing access, billing, and grouping related work     |
| [**Extraction Schemas**](/concepts/02-extraction-schemas)               | Definitions that specify what data to extract and how to structure it          |
| [**Collectors**](/concepts/03-collectors)                               | Entry points that feed documents into the system (uploads, URLs, integrations) |
| [**Extractions**](/concepts/04-extractions)                             | The processed results containing structured data from your documents           |

## Use Cases

Sterndesk is built for software teams handling document-heavy workflows:

* **Maritime & logistics** — Process cargo manifests, bills of lading, and shipment documents
* **Ocean enterprise** — Extract data from vessel reports, port documentation, and regulatory filings
* **Research & academia** — Structure data from scientific papers, surveys, and institutional records
* **Compliance & legal** — Parse contracts, audit reports, and regulatory submissions
* **Enterprise operations** — Automate invoice processing, procurement documents, and internal records

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/get-started/02-quickstart">
    Make your first API call in minutes
  </Card>

  <Card title="Authentication" icon="key" href="/get-started/03-authentication">
    Set up API keys and access tokens
  </Card>
</CardGroup>