Bruin Academy

Guide

Build an AI Data Analyst

Set up a local AI data analyst that can read your warehouse context, use Bruin MCP, and answer the first business question with SQL-backed analysis.

Quick overview of the full setup

What

Create a Bruin project that gives an AI data analyst the context it needs to answer warehouse questions safely. You will import schema metadata, add descriptions and quality checks, wire an AI coding tool to Bruin MCP, and ask the first SQL-backed business question.

By the end, you will be able to:

  • Create a Bruin project to hold warehouse metadata, quality checks, and agent instructions
  • Connect BigQuery, Redshift, ClickHouse, or Postgres so Bruin can import schema and run queries
  • Wire Cursor, Claude Code, or Codex to Bruin MCP and ask the first analysis question

How

Start with an empty Bruin project and add a read-only warehouse connection. Import and enhance table context before giving the agent query access, then use AGENTS.md and optional glossary/docs context to keep answers grounded.

Before you start

Get help & contribute

Sign up to our newsletter

Practical updates on open-source data pipelines, AI analysts, governance, and what we are shipping at Bruin.