Talks

This session goes beyond the flashy demos—no more “Look ma, it built Flappy Bird!” Instead, we bring engineering rigor to the messy, magical world of AI-assisted code generation. As more developers rely on large language models (LLMs) to write code, one thing becomes clear: testing is not optional—it’s our compass, our seatbelt, and our sanity check.

We’ll tackle the real questions developers are facing right now:
  • How can AI help us write meaningful tests?
  • How do we effectively test applications that use LLMs?
  • And how do we define what “good” looks like when the code isn’t fully human-written?

More than just catching bugs, tests become a powerful way to make sense of the codebase, clarify intent, and ensure quality in systems we no longer fully control. This talk offers practical strategies, developer insights, and a few battle scars from working with AI in the loop.


Patrick Debois
Humans and Code
Patrick is a true pioneer—credited with coining the term DevOps, co-authoring the DevOps Handbook, and launching the very first DevOpsDays back in 2009. Since then, he’s been shaping the tech industry with his unmatched ability to bring development, operations, and now GenAI together in truly transformative ways.

Here’s why you don’t want to miss him:
🔹 Independent consultant at the cutting edge of GenAI and DevOps
🔹 Fractional CTO, advisor, and workshop leader
🔹 Former VP of Engineering, Distinguished Engineer, CTO
🔹 Guided teams at industry giants like Atlassian and Snyk
🔹 Contributor and advisor at AI Native Dev Community
🔹 Active speaker, community builder, and lifelong learner

Patrick is all about raising the bar—helping companies embed engineering rigour into their GenAI journeys, inspiring teams to embrace AI for automation, and advising GenAI platforms on how to truly deliver value. He bridges the gap between management and engineering with a rare mix of deep tech expertise and people-first thinking.