Building with AI, DuckDB + RDF, and the Semantic Future w/ Dan Bennett (Head of Tech @ S&P Global)

On this episode of The Joe Reis Show, I’m joined by Dan Bennett, Head of Technology for the Enterprise Data Organization at S&P Global. We get into what it actually looks like to build with modern AI coding tools like Claude Code. Not just as a toy, but for writing production-grade C++. Dan walks through how he built an open-source RDF extension for DuckDB, why rock-solid test coverage is non-negotiable when working with LLMs, and why engineering leaders need to keep their hands dirty to understand where this tech is headed. We also react to the breaking news of AWS acquiring DuckDB Labs, talk through the shift from "human-in-the-loop" to autonomous agents running in headless VMs, and dive into why data semantics across organizational boundaries remains one of the hardest - and most important - unsolved problems in our industry. Website: https://nonodename.com/ Timestamps: 00:00 – Intro & Dan Bennett's Background at S&P Global 01:19 – Building an Open-Source RDF Extension for DuckDB with AI 06:18 – How Coding Has Shifted: Writing Modern C++ with Claude 08:24 – Why Engineering Leaders Must Stay Hands-on 10:40 – The Impact of GenAI on Engineering Teams & Cycle Times 14:03 – Moving from the IDE to Autonomous "Human-on-the-Loop" Agents 18:27 – Navigating Team Dynamics, ROI, and Career Advice for Junior Devs 23:52 – Why RDF on DuckDB? Solving Unsolved Data Problems 25:51 – Reacting to AWS Acquiring DuckDB Labs 34:29 – Semantic Interoperability & Crossing Organizational Boundaries 44:14 – Politics vs. Tech in Data Semantics & Tying Work to Business Value 48:48 – Frontier LLMs, Embodied AI, and What's Next 51:23 – Where to Find Dan Bennett & Outro