This step is optional. Your AI analyst already works without these additions. Steps 1–5 give you a fully functional setup. The techniques below help you push the agent's understanding further, but you can skip ahead or come back to this later.

Why this step matters

By now your AI analyst works - it knows your schema, understands your domain terms, and can query your warehouse. But there's a ceiling. The context it relies on is limited to what's in your AGENTS.md and your asset files. Your organization almost certainly has richer knowledge sitting elsewhere: internal wikis, product specs, data dictionaries maintained by other teams, and business rules documented in Notion or Confluence.

This step shows you two ways to push past that ceiling:

1. Bruin Glossary - a structured, version-controlled dictionary of business entities and their attributes that Bruin uses to keep column definitions consistent across assets
2. External MCP servers - connect your AI tool to Notion or Confluence so the agent can pull context directly from your team's existing documentation

Neither is required. Your analyst already works without them. But both make it significantly better at understanding the nuances of your business.