Welcome to Bauplan
Bauplan brings Git-style workflows to data so AI agents can safely make changes on your data.
You can run AI-generated pipeline changes on real production datasets while keeping your data and downstream applications protected, with a clean rollback path if something goes wrong.
Bauplan provides a tight, tool-callable loop with a small API surface: write to an isolated branch, run and validate, then publish to main with an atomic merge. If a change fails validation or causes issues later, roll back to a previous commit.
Use Bauplan for workloads where you produce and maintain tables: ingesting files into curated datasets, building transformation pipelines, running backfills, enforcing data quality tests, and iterating quickly on logic and outputs.
In your architecture, Bauplan sits on top of your object storage and manages data as Iceberg tables. It produces versioned Iceberg outputs that remain compatible with any Iceberg-capable engine and catalog, so you can keep your existing tools for analytics and BI while using Bauplan as the execution and change-management layer for pipelines and agent workflows.
📚 Learn more →
Get Started
Manage Bauplan from AI Tools
Control Bauplan lakehouse from your favorite AI tools using simple, conversational commands with our MCP Server.