Dagster Running Dagster: How We Use Compass for AI Analytics
In this Deep Dive, we're joined by Dagster Analytics Lead Anil Maharjan, who demonstrates how our internal team utilizes Compass to drive AI-driven analysis throughout the company.
Most people don't actually know what they want from data. They have a vague question, a hunch, or a half-formed hypothesis. Analysts spend a huge amount of time just figuring out the right path forward before any real analysis begins.
At Dagster, we've been using Compass internally to change that. For simple questions, it eliminates context switching and frees up cognitive overhead. For complex queries, it helps guide analysts down the right path when there are dozens of directions to explore.
In this session, Anil walks through how Compass has increased our data team's capacity, shares best practices for data modeling that work well with AI assistants (hint: nested columns and wide tables are your friends), and demos a real case where our Compass Dagster+ integration identified the root cause of a Postgres-to-Snowflake pipeline that was failing 40-50% of the time.
.jpg)
