> ## Documentation Index
> Fetch the complete documentation index at: https://docs.landing.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Overview
> Learn how ADE converts documents into structured data and when to use the Parse, Extract, and Ground APIs.
[Agentic Document Extraction](https://ade.landing.ai/) (ADE) is a document intelligence platform that converts documents into reliable, structured data. Use the structured data to build retrieval-augmented generation (RAG) applications, power intelligent search systems, extract key information, and automate document processing.
ADE is powered by the **DPT-3** family of models, built for the era of AI agents and agentic workflows and designed around feedback from users running document-intensive workloads.
## How ADE Works
Agentic Document Extraction provides three APIs for document processing: [Parse](./parse), [Extract](./extract), and [Ground](./ground).
Most workflows start with **Parse**, which converts a document into structured data. After parsing, you can use **Extract** to pull specific data fields from the Markdown, and **Ground** to map each extracted field back to its location on the page.
| API | Description | When to Use |
| - | - | - |
| [Parse](./parse) | Converts PDFs, images, Office text documents, presentations, and spreadsheets (XLSX and CSV) into reading-order Markdown, a hierarchical structure of pages and blocks, and per-block grounding. | Use to convert documents into structured data for downstream applications, such as RAG, search, and agents.
Most workflows start here. |
| [Extract](./extract) | Pulls specific data fields from Markdown using schema-based extraction. | Use when you need the values of specific fields.
Works best on Parse output. |
| [Ground](./ground) | Maps each extracted field back to the blocks it was quoted from, returning block ids, page numbers, and bounding boxes. | Use when you need to highlight, cite, or review where extracted values appear on the page.
Runs on Parse and Extract output. |
Parse and Extract each run as [synchronous requests or async jobs](./sync-async). Use [Parse Jobs](./parse-async) and [Extract Jobs](./extract-async) for large files and background pipelines. Ground always runs synchronously and consumes no credits.
## Key Capabilities
* **Designed for agent systems.** Built around how downstream AI agents consume document data: semantic block ids, predictable hierarchy, and Markdown ranges so you can map results back to source.
* **Hierarchical layout model.** The structured output is a nested hierarchy: pages, blocks on each page, and cells within tables.
* **Fine-grained visual grounding.** Bounding boxes for every block, plus per-line or per-word boxes through each block's atomic grounding, so you can highlight or extract content at the line or word level.
* **Clean, standardized Markdown.** Structured figure elements with classification labels, bracketed attestation and scan-code labels, and standardized checkboxes.
## Important to Know
* Parse supports **PDFs, images, Office text documents and presentations** (DOCX, PPTX, ODT, RTF), **and spreadsheets** (XLSX, CSV). Legacy binary Office files (DOC, PPT) are not supported; for those, use [Parse Gen1](/ade/parse). See [Supported File Types](./file-types).
* **Password-protected files** are not supported. Decrypt the file and submit an unencrypted copy.
* Upgrading from ADE Gen1? The endpoints and response shapes changed. See the [Migration Guide](./migration-guide).
## Find What You Need
Pick a starting point based on what you want to do.
See Parse in action without writing code. Upload a file in your browser.
Make your first API call: parse a document and get structured Markdown back.
Understand the response shape: pages, blocks, and grounding.
Parse and extract your own documents from the terminal, with results saved on your machine.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.