# DataFlint

> DataFlint enriches your Apache Spark logs and serves them to AI agents through a Spark MCP server, so they ship fixes that actually cut Spark runtime and cost. The agentic platform spans four offerings: an IDE copilot, a cluster right-sizing agent, a PR review agent, and company-wide fleet observability.

## Products

- [Agentic Spark Copilot](https://www.dataflint.io/product/spark-copilot): Production-aware IDE copilot powered by enriched Spark logs and the Spark MCP server.
- [Cluster Agent](https://www.dataflint.io/product/cluster-agent): Right-sizes Spark clusters in real time using your enriched Spark logs.
- [Review Agent](https://www.dataflint.io/product/review-agent): Reviews every pull request with enriched production context from the Spark MCP server.
- [Fleet Observability](https://www.dataflint.io/product/fleet-observability): Company-wide Spark cost and performance dashboard built on enriched Spark logs.

## Resources

- [Product Overview](https://www.dataflint.io/product): The agentic Apache Spark platform powered by enriched Spark logs and the Spark MCP server.
- [How it Works](https://www.dataflint.io/resources/how-it-works): Technical architecture and how enriched Spark logs reach your agents.
- [Use Cases](https://www.dataflint.io/resources/use-cases): Real-world results, including a 100x cost reduction at SimilarWeb.
- [Blog](https://www.dataflint.io/resources/blog): Engineering and product writing on Apache Spark optimization.
- [Pricing](https://www.dataflint.io/pricing): Open source and SaaS plans.
- [Documentation](https://dataflint.gitbook.io/dataflint-for-spark/): Getting started and reference docs.

## Open Source

- [DataFlint for Spark on GitHub](https://github.com/dataflint/spark): Open-source Spark Web UI for monitoring and debugging Spark jobs.