How do I build self-healing data pipelines?
Quality checks gate each asset, failures stop downstream runs, and retries with alerts recover transient errors, so a pipeline catches and contains its own breakages instead of shipping bad data. Bruin does this in one platform: ingestion, SQL and Python pipelines, quality checks, lineage, and an AI data analyst that answers in Slack, Microsoft Teams, Google Chat, WhatsApp, Discord, Telegram, email and the browser.
Command
bruin runDefined in
SQL + YAML
Works with
Bruin CLI + Bruin Cloud
What you get
How it works in code
columns:
- name: amount
checks:
- name: not_null
- name: non_negative
custom_checks:
- name: row_count_within_bounds
query: SELECT COUNT(*) BETWEEN 1000 AND 100000 FROM {{ this }}Run bruin run and Bruin blocks downstream assets when a check fails.
About Bruin
What is Bruin?
Bruin is an open-source, AI-powered data platform. One project covers the whole path from source to answer: data ingestion (with ingestr), SQL and Python transformations, quality checks, column-level lineage, a data catalog and scheduling. On top of that data, an AI data analyst answers questions in Slack, Microsoft Teams, Google Chat, WhatsApp, Discord, Telegram, email or the browser, and builds dashboards from a prompt.
Pipelines are plain SQL, Python and YAML files in your own Git repository, and the work runs inside your own warehouse: Snowflake, BigQuery, Databricks, Redshift, Postgres, ClickHouse, DuckDB and others. The Bruin CLI is open source under Apache 2.0 and runs on a laptop, in CI or on-prem. Bruin Cloud is optional and adds scheduling, the AI data analyst, governance, SSO and audit logs.
For AI agents that means governed access to your data and pipelines over MCP or an API, with the context an agent needs to get the answer right.
- Replaces
- Separate tools for ingestion, transformation, orchestration, data quality, cataloguing and BI
- Open source
- Bruin CLI under Apache 2.0; ingestr source-available under the Functional Source License
- Your data
- Stays in your warehouse; pipelines stay in your Git repository
- Security
- ISO/IEC 27001:2022 certified and SOC 2 Type 2 attested
- Used by
- Data teams at Lessmore, StarBerry, NativeMinds, SCG, M8 Games and Fabrikatör
Why Bruin for AI agents
MCP for coding agents
bruin mcp gives Claude Code, Cursor, VS Code and Codex tools to query data, compare tables, ingest data and build pipelines.
Read-only by default
The Bruin Cloud Query API rejects any statement that is not a SELECT or WITH query, keeps credentials in Bruin and records every query in an audit log.
Context, not just tables
Agents read semantic models, the glossary, column descriptions and AGENTS.md files, so they use your definitions instead of guessing.
Scoped tokens
Personal and team tokens carry only the permissions an agent needs.
How it works
01
Install the CLI
Install Bruin and point it at your project and warehouse.
02
Connect the agent
In Claude Code, run claude mcp add bruin -- bruin mcp. Other clients use the same server.
03
Add definitions
Define metrics in a semantic model so the agent asks for them by name.
Give agents governed data
Bruin CLI and ingestr are on GitHub.
A demo walks through your own data.