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

# Introduction

> Reworkd - Extract web data at scale

<Frame>
  <img src="https://mintcdn.com/reworkd/858NO5gKC4Mh2QRA/images/banner.png?fit=max&auto=format&n=858NO5gKC4Mh2QRA&q=85&s=28b9277ef22252d328f000a757ab7f4d" width="1270" height="760" data-path="images/banner.png" />
</Frame>

Reworkd uses LLMs to parse, understand, and interact with web pages to help users scrape web data at ***scale***.
Reworkd customers are extracting millions of rows of data to help build data constrained products, fine tune domain specific language models, and enrich existing data pipelines.

<Info>
  We also built AgentGPT! If you're looking for info on AgentGPT, please visit our
  [Github](https://github.com/reworkd/AgentGPT)
</Info>

<CardGroup cols={2}>
  <Card title="Build your first scraper" icon="lightbulb" href="https://app.arcade.software/share/6GkFKiXytq3lXQU3JWAx">
    Learn how to scrape a website and its sub pages with Reworkd
  </Card>

  <Card title="Key terms" icon="brain" href="/key-concepts">
    Understand all of the key terms required to get started
  </Card>

  <Card title="Exporting data" icon="globe" href="/features/exports/overview">
    Learn how to export the data you scrape
  </Card>

  <Card title="Blog" icon="rss" href="https://www.reworkd.ai/blog">
    Read the latest updates on the Reworkd blog
  </Card>
</CardGroup>