Bruin Academy

Build an AI Data Analyst

Go from zero to a working AI analyst that understands your database, speaks your domain language, and answers real business questions.

What is this?

An open-source, DIY approach to building an AI data analyst. You use Bruin's CLI tools to map your database schema into context files that any AI coding assistant can read — then the AI can query your data directly.

How it works: Bruin CLI introspects your warehouse and generates asset files with schema, column descriptions, and domain context. Bruin MCP connects this to your AI tool, giving it direct query access.

No vendor lock-in, no SaaS dependency — just open-source tools you run locally.

▶ Watch the tutorial: Claude + BigQuery for Finance →

What you'll build

By the end of this module you will have an AI agent that connects to your data warehouse, understands your schema and business terms, and answers questions with real SQL queries.

The core setup takes about 1–2 hours (Steps 1–5), depending on the size of your database and how much troubleshooting is needed. The AI enhance step (Step 3) alone can take several minutes for larger schemas. Step 6 covers optional ways to enrich your context further — you can skip it initially and come back later.

Before you start