MCP/Agentic data engineeringData Engineer

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.

Get Bruin on GitHub How MCP works

Command

bruin run

Defined in

SQL + YAML

Works with

Bruin CLI + Bruin Cloud

What you get

Checks as gatesstop-on-failureretries and alerts

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.