Dumky de Wilde
I spent over 10 years as a consultant setting up data pipelines, data models, and cloud infrastructure for clients ranging from government to fintech to retail and energy, before joining MotherDuck to help people and their AI agents make the most of the platform through documentation, examples, and other content.
I am the co-author of The Fundamentals of Analytics Engineering, and I love writing about all things data — both at MotherDuck and on my personal blog at dumky.net.
Session
Is it still worth learning SQL in 2026, or can we just "chat" with our data? This hands-on tutorial explores that exact question by pushing Text-to-SQL to its absolute limits. This won't be just happy paths; we will deliberately expose where LLMs fail : ambiguity, hallucinations, and "dirty" data...and build the engineering stack required to fix them!
You will build a local data Agent from scratch using DuckDB, MCP and a minimalist semantic layer. By the end, you will understand the hard boundaries of AI reasoning, how a semantic layer acts as a safety net, and why knowing SQL is still (since 1974) the most critical skill for building reliable analytics agents.