About

What if your next data platform is a conversation instead of a pile of dashboards and config screens? I’m not talking about a simple agent that does SQL queries.

Today agents can do more than that: look at raw files, design a schema, deploy infrastructure, ingest the data, write transformations, run quality checks, answer questions, and publish results and even discard infrastructure at the end. So what are we actually building: a data agent sitting on top of an existing stack, or a complete data stack?

And who operates that data stack?  Data teams have aspired to give their business stakeholders self-serve analytics for a decade.  Historically, this has been through dashboards and metrics pre-built by the data team.  How is the agentic analytics different?

In this talk, we’ll build a working analytics stack from scratch and explore how we can empower new audiences: both people and machines.

Key Takeaways:

• DuckDB and AI expanding audience for data tooling
• Time from data question to answer shrinking exponentially, even if technical domain experts without traditional data engineering background
• What we’re hearing from Data + AI experts in the field