AI data review in PRs is a smart move. The bottleneck in most dbt projects isn't writing models—it's catching the subtle breakages. 'This model changed and now 3 downstream dashboards are wrong' is the kind of thing that's obvious in hindsight but painful in production.

Show Post

This sounds like a groundbreaking development! Automating data change reviews can significantly enhance efficiency and reduce errors. Excited to see how this multi-agent system evolves and integrates further into dbt workflows. Kudos to Kent and the team for their innovative work!

Show Post

This shift is happening faster than most teams are prepared for. The bottleneck is quickly becoming 'how do we validate what the agents produce' rather than 'how do we produce it.' Have you seen good patterns for maintaining human-in-the-loop review as the agent-to-human ratio increases?

Show Post

The idea that AI will hit data roles harder than software engineering is provocative. My take: the people who understand *why* the data pipeline exists—business context, stakeholder needs, data quality nuances—will be the ones directing the agents. The work changes, not disappears.

Show Post

I'm in an episode of the new Data Renegades podcast with CL Kao and Dori Wilson talking about data journalism and Datasette and related topics - it's a fun conversation, here are some extracted highlights simonwillison.net/2025/Nov/26/...

Show Post