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

# Cloudsquid Documentation

> AI-powered document extraction and workflow automation.

Cloudsquid turns unstructured documents into structured data — and connects that data to your systems.

## Where do you want to start?

<CardGroup cols={2}>
  <Card title="Extraction Agent Quickstart" icon="robot" href="/quickstart">
    Upload files, define a schema, and start extracting structured data in minutes.
  </Card>

  <Card title="Workflow Builder Quickstart" icon="diagram-project" href="/quickstart_workflow">
    Connect an email trigger to an extraction agent and push results to Google Sheets.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Integrate extraction and reconciliation directly into your application.
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/concepts/table-types">
    Understand table types, pipelines, and the async run pattern.
  </Card>
</CardGroup>

## What can you do?

<CardGroup cols={3}>
  <Card title="Extract" icon="file-export">
    Upload PDFs, images, spreadsheets, audio, or video. Define a schema. Get structured JSON back — no code required.
  </Card>

  <Card title="Reconcile" icon="arrows-rotate">
    Validate and match extracted data against reference tables using AI agents. Flag discrepancies automatically.
  </Card>

  <Card title="Automate" icon="bolt">
    Connect triggers (email, webhook) to actions (extraction, Sheets, databases) in the no-code Workflow Builder.
  </Card>
</CardGroup>

## Quick API example

Extract a PDF and get structured data in a single call.

<CodeGroup>
  ```python Python theme={null}
  import requests, base64

  with open("invoice.pdf", "rb") as f:
      file_b64 = base64.b64encode(f.read()).decode()

  response = requests.post(
      "https://api.cloudsquid.io/api/projects/my-project/tables/TABLE_ID/extract",
      headers={"X-API-Key": "YOUR_API_KEY"},
      json={
          "file": file_b64,
          "filename": "invoice.pdf",
          "mimetype": "application/pdf",
          "file_type": "binary"
      }
  )
  print(response.json()["data"])
  ```

  ```bash cURL theme={null}
  curl -X POST \
    "https://api.cloudsquid.io/api/projects/my-project/tables/TABLE_ID/extract" \
    -H "X-API-Key: YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "file": "'$(base64 -i invoice.pdf)'",
      "filename": "invoice.pdf",
      "mimetype": "application/pdf",
      "file_type": "binary"
    }'
  ```
</CodeGroup>

<Note>
  Questions? Email [info@cloudsquid.io](mailto:info@cloudsquid.io) or visit the [blog](https://cloudsquid.substack.com/).
</Note>