This session is a "reality check" for AI analytics. We combine theory with engineering to answer one question: Where are the limits of Text-to-SQL? Participants will experience the frustration of a hallucinating LLMs and the satisfaction of fixing it with a realistic minimalist local setup.
Learning objectives:
- Map the limits: Identify exactly where LLMs break (e.g., complex joins, specific business logic, non-standard schemas).
- Bridge the gap: Learn how a semantic layer translates fuzzy English into deterministic SQL.
- Modern architecture: Overview and hands-on on DuckDB Model Context Protocol (MCP) to give agents standard, safe tools to do analytics.
- The verdict: Understand why SQL is becoming the "Assembly Language" of the AI era, and why you still need to be fluent in it and what is still missing to just "chat with our data".
Prerequisites:
- Laptop with Python 3.10+.
- Beginner SQL knowledge (joins, aggregations).
- No prior AI/LLM experience required.
Mehdi Ouazza
I started my career in data 10+ years ago as a data engineer, working in large corporates like AXA setting up on-prem Spark clusters (yes, that old!) to tech unicorns building data platforms in the cloud at Klarna, Back Market, and Trade Republic.
Over the years, I found a passion for sharing what I learned and teaching others. It became my full-time job when I joined as the first DevRel at MotherDuck (DuckDB in the cloud) in 2023.
I believe learning should be fun. I enjoy making complex topics more approachable through storytelling and creativity.
I want to keep teaching curious students (in-person and online) and help the next generation learn not just data, but software engineering in this post-AI world.
