Best Practices for LLM Dagster Development

The abstractions for LLM code generation have come a long way since 2023. Planning, sub-agents, skills, MCP; tools like Claude Code and Cursor have changed what's possible.

However, Models don't know your project. They don't know Dagster's idioms, your pipeline conventions, or the specific context that makes code actually useful. This disconnect turns many people off when they get frusturated and they are leaving a lot of productivity on the table.

We've been building infrastructure to close that gap. Join us for a practical look at LLM development for data engineering best practices, common pitfalls, and live demos of what works.