Skip to main content
Build and deploy your first Buster agent in just 10 minutes. You’ll need:
  • A GitHub account with admin access to a repository
  • A data warehouse (Snowflake, BigQuery, Redshift, etc)
  • Warehouse credentials

​
1. Connect your stack

Go to our website and create an account. When prompted, install the Buster GitHub App on your repository. Choose “All repositories”, or select specific repos. Connect the GitHub App You will then be prompted to connect your data warehouse. See the Data Warehouse integrations section for connection details specific to your warehouse (Snowflake, BigQuery, Redshift, etc.).

​
2. Create an agent

Create a file at .github/buster/agents/pr-greeter.yaml in your repository:
pr-greeter.yaml
name: pr-greeter
description: Comments on pull requests with a friendly summary

triggers:
  - type: pull_request
    events: [opened, synchronize]

tools:
  preset: safe  # Read-only tools

prompt: |
  You are a helpful PR assistant. When a pull request is opened or updated:
  
  1. Read the PR title, description, and list of changed files
  2. Count the total files changed
  3. Add a friendly comment to the PR with:
     - A greeting
     - The number of files changed
     - The types of files modified (e.g., "Python files", "SQL models", "config files")
  
  Keep your comment concise and friendly.
Commit and push to your main branch. Buster will automatically detect and deploy your agent within seconds.

​
3. Test your agent

Create a test branch and open a pull request. Within 60 seconds, you’ll see a comment from Buster with a friendly summary of your changes. You can go to the “Runs” tab in the web app to see the full execution log, including which tools the agent used and all inputs/outputs.

​
4. Explore more examples

Auto-Update Documentation

Keep your dbt documentation up to date by automatically profiling models and generating comprehensive YAML documentation.

Breaking Change Detection

Review dbt code for breaking changes before they reach production with automated impact analysis.

Schema Change Detection

Automatically detect and adapt to schema changes in your data warehouse before they break downstream pipelines.

Cost Monitoring

Monitor warehouse costs and detect expensive queries before your bill explodes.

Data Freshness Monitoring

Build agents that continuously monitor data freshness and alert your team when data goes stale.