Workshops
Hands-on sessions I run on building with AI without lowering the bar. Each one also works as a shorter talk for a conference, meetup or engineering day.
Building an AI system you can actually measure
A minimum viable evaluation setup for RAG and assistants, and what to do when the numbers say your design decision was wrong.
Workshop or talkFrom 22 AI buttons to one useful decision
Turning an AI toolbox into guidance: why equal-weight actions fail, and how to recommend one next step from real state.
Workshop or talkRAG that knows when to shut up
Designing assistants that abstain, degrade and cite honestly, because a confident wrong answer does more damage than "I don't have that".
Workshop or talkAI writes code. You still own the failure.
A hands-on session on the gates that catch what code review misses when a model writes part of your code.