> ## 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

> Documentation for Datafold Classic, with data diffs, CI/CD testing, data monitoring, lineage, and the MCP server, on app.datafold.com, eu.datafold.com, and Classic Dedicated Cloud deployments.

> [!NOTE]
>
> **These docs cover the Datafold application only.** They do not cover Datafold's AI agent platform, which our team uses to deliver migrations and other data engineering projects. The platform is changing quickly, so we share its capabilities directly rather than in public docs. To learn what it can do for your project, [book a demo](https://www.datafold.com/demo).

> [!NOTE]
>
> You are reading the docs for **Datafold Classic** (`app.datafold.com`, `eu.datafold.com`, or a Classic Dedicated Cloud deployment). If you sign in at `us.datafold.com`, `eub.datafold.com`, or a deployment set up for a migration project, switch to **Current** in the version menu. Not sure? See [Which version am I on?](https://docs.datafold.com/classic/which-version.md)

## Key features

> **[Data Platform Migrations](https://docs.datafold.com/classic/data-migration-automation/datafold-migration-agent.md)**
>
> The Data Migration Agent delivers guaranteed-outcome migrations with fixed price, timeline, and data parity — over 6x faster than traditional approaches.

> **[Data Explorer & Lineage](https://docs.datafold.com/classic/data-explorer/how-it-works.md)**
>
> Explore lineage, business logic, and usage metadata across your data ecosystem.

> **[Data Quality & CI/CD](https://docs.datafold.com/classic/data-diff/what-is-data-diff.md)**
>
> Value-level data diffs, monitors, and reconciliation power tools — exposed via MCP so your coding agents can validate their own work.

> **[MCP Integration](https://docs.datafold.com/classic/datafold-mcp.md)**
>
> Connect your AI coding agent to Datafold and interact with your data through natural language — diffs, lineage, monitors, and more.

## Use cases

> **[Data Platform Migrations](https://docs.datafold.com/classic/data-migration-automation/datafold-migration-agent.md)**
>
> Modernize your data platform in weeks, not years, with AI-powered migration automation and cross-database validation.

> **[AI-Assisted Data Development](https://docs.datafold.com/classic/datafold-mcp.md)**
>
> Supercharge your coding agents with data quality tools via MCP.

> **[CI/CD Testing & Monitoring](https://docs.datafold.com/classic/deployment-testing/how-it-works.md)**
>
> Automatically test, data-diff, and validate every pull request before it reaches production.

## Getting started

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

**1. Create a data diff**

Once you’ve integrated a [data connection](https://docs.datafold.com/classic/integrations/databases.md) and [code repository](https://docs.datafold.com/classic/integrations/code-repositories.md), you can run a new [in-database](https://docs.datafold.com/classic/data-diff/in-database-diffing/creating-a-new-data-diff.md) or [cross-database](https://docs.datafold.com/classic/data-diff/cross-database-diffing/creating-a-new-data-diff.md) data diff or explore your [data lineage](https://docs.datafold.com/classic/data-explorer/lineage.md).

**2. Create automated monitors**

Create [monitors](https://docs.datafold.com/classic/data-monitoring/monitor-types.md) to send alerts when data diffs fall outside predefined ranges.

**3. Set up CI/CD testing**

Get started with deployment testing through our universal ([No-Code](https://docs.datafold.com/classic/deployment-testing/getting-started/universal/no-code.md), [API](https://docs.datafold.com/classic/deployment-testing/getting-started/universal/api.md)) or [dbt](https://docs.datafold.com/classic/integrations/orchestrators/dbt-core.md) integrations.

## Learn more

* [Connect your AI agent to Datafold via MCP](https://docs.datafold.com/classic/datafold-mcp.md) 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/demo) to see how Datafold can automate your data engineering workflows


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.