Why AI Agents Will Break Modern Data Engineering (And How to Fix It) w/ Christophe Blefari (Nao)

In this episode of The Joe Reis Show, I catch up with my good friend Christophe Blefari, co-founder of NAO, to dig into what's actually happening on the front lines of AI agents and data engineering. We talk about the evolution from building SQL IDEs to agentic analytics harnesses, how prompt-driven workflows are reshaping data teams, and why age-old problems like data discovery, modeling, and documentation are suddenly roaring back. We also dive into the risks of "token slop," whether data and software engineering roles are destined to merge, Christophe’s take on DuckDB’s acquisition by AWS, and the realities of building AI tools across Europe and the US. Nao: https://getnao.io/ Timestamps 00:00 – Catching up & introducing NAO 02:16 – Moving past SQL IDEs to agentic analytics harnesses 05:40 – The evolving role of the data analyst & prompt-driven workflows 08:33 – Unsolved challenges: Data discovery, documentation, and agent context 11:18 – The dual layer: Agentic infrastructure vs agentic consumption 14:06 – Auto-maintaining documentation and the risk of agent "token slop" 18:44 – Experimenting with autonomous data modeling & semantic contracts 22:25 – Semantic layers, feature stores, and the great convergence 25:41 – Will data roles converge or stay specialized? 31:24 – Task-based automation vs replacing full human roles 36:16 – Internal workflows: Managing synchronous vs asynchronous coding agents 42:16 – Creative friction: When AI memories derail human reasoning 45:15 – European tech landscape: DuckDB acquired by AWS & market shifts 52:36 – Local hardware, Mac Minis for inference, and distributed compute 55:59 – Tech fatigue, upcoming IPOs, and wrap-up