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

# Datafold

> Datafold is the data engineering automation platform that combines specialized AI agents with a context layer and data quality tools — so data teams and their coding agents ship higher-quality data faster, migrate with confidence, and optimize platform costs.

## Key features

<CardGroup cols={2}>
  <Card title="Data Platform Migrations" href="/data-migration-automation/datafold-migration-agent" horizontal>
    The Data Migration Agent delivers guaranteed-outcome migrations with fixed price, timeline, and data parity — over 6x faster than traditional approaches.
  </Card>

  <Card title="Data Knowledge Graph & Lineage" href="/data-explorer/how-it-works" horizontal>
    The context layer for reliable AI-assisted data engineering — lineage, business logic, usage, and ontology served via MCP to your coding agents.
  </Card>

  <Card title="Data Quality & CI/CD" href="/data-diff/what-is-data-diff" horizontal>
    Value-level data diffs, monitors, and reconciliation power tools — exposed via MCP so your coding agents can validate their own work.
  </Card>

  <Card title="MCP Integration" href="/datafold-mcp" horizontal>
    Connect your AI coding agent to Datafold and interact with your data through natural language — diffs, lineage, monitors, and more.
  </Card>
</CardGroup>

## Use cases

<CardGroup cols={3}>
  <Card title="Data Platform Migrations" href="/data-migration-automation/datafold-migration-agent" horizontal>
    Modernize your data platform in weeks, not years, with AI-powered migration automation and cross-database validation.
  </Card>

  <Card title="AI-Assisted Data Development" href="/datafold-mcp" horizontal>
    Supercharge your coding agents with the Data Knowledge Graph and data quality tools via MCP.
  </Card>

  <Card title="CI/CD Testing & Monitoring" href="/deployment-testing/how-it-works" horizontal>
    Automatically test, data-diff, and validate every pull request before it reaches production.
  </Card>
</CardGroup>

## Data Knowledge Graph

<Info>
  **Private Beta** — The Data Knowledge Graph is currently in private beta. Contact the Datafold team at [sales@datafold.com](mailto:sales@datafold.com) to enable this for your organization.
</Info>

The **Data Knowledge Graph (DKG)** automatically collects and unifies all information about your data ecosystem — lineage, business logic, usage statistics, BI connections, git history, and organizational knowledge — and serves it to your AI agents via MCP.

Unlike data catalogs that rely on manual curation, the DKG is sourced and maintained by AI, and optimized for consumption by the coding agents of your choice. It spans all your data sources and code bases, creating a comprehensive view of your entire data platform that is inaccessible to any single provider on their own.

The DKG powers Datafold's specialized agents (such as the Data Migration Agent) and supercharges external coding agents (Claude Code, Cursor, Windsurf) by providing the context they need to produce reliable results for any data engineering task.

## Getting started

There are a few ways to get started with your first data diff:

<Steps>
  <Step title="Create a data diff" stepNumber="1">
    Once you’ve integrated a [data connection](/integrations) and [code repository](/integrations/code-repositories), you can run a new [in-database](/data-diff/in-database-diffing/creating-a-new-data-diff) or [cross-database](/data-diff/cross-database-diffing/creating-a-new-data-diff) data diff or explore your [data lineage](data-explorer/lineage).
  </Step>
</Steps>

<Steps>
  <Step title="Create automated monitors" stepNumber="2">
    Create [monitors](data-monitoring/monitor-types) to send alerts when data diffs fall outside predefined ranges.
  </Step>
</Steps>

<Steps>
  <Step title="Set up CI/CD testing" stepNumber="3">
    Get started with deployment testing through our universal ([No-Code](deployment-testing/getting-started/universal/no-code), [API](deployment-testing/getting-started/universal/api)) or [dbt](integrations/orchestrators/dbt-core) integrations.
  </Step>
</Steps>

## Learn more

* [Connect your AI agent to Datafold via MCP](datafold-mcp) and start using data diffs, lineage, and monitors from your development environment
* Read our [Data Quality Guide](https://www.datafold.com/data-quality-guide) for a practical roadmap to building a robust data quality system
* [Book a demo](https://www.datafold.com/) to see how Datafold can automate your data engineering workflows