
There are two common ways to get AI to make a chart today: ask a BI tool, or accept a pile of generated code that no one can read. Neither gives a data team much to review, test, or govern. In this episode of The Analytics Engineering Podcast, Tristan talks with Dave Fowler, founder of Chartio and the creator of dbt Charts. Dave started Chartio back in 2010 and sold it to Atlassian. Now he's back, building what he calls "the Markdown of dashboards": a human-readable spec that AI can write and people can review. They discuss why AI-generated charts need to be auditable. They dig into the BI bottleneck, including Dave's take that AI could make dimensional modeling less necessary. And they explore where dashboards go when agents start spinning them up on demand. You can check out dbt Charts at dbtcharts.com. The Analytics Engineering Podcast is sponsored by Fivetran + dbt Labs. Discover why more than 80,000 data teams use dbt to accelerate their data development.
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

Can data agents do real analysis?

Open data infrastructure and AI agents (George Fraser & Martin Casado)

Roundup: Personal agents, AI policy, GPT-6.1 Astra, and Jev decision models

You don't have ICs anymore, you have managers (Emilie Schario)
Free AI-powered recaps of The Analytics Engineering Podcast and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.