AI Native Dev - Munich Meetup
AI is changing software development. We're really excited and intrigued by the future of it:
Maybe you are building software with AI?
Or building tools that build software with AI?
Then this meetup is for you. No product pitches, all experience from the trenches. And it's becoming a tradition now, if you're attending the InfoQ Dev Summit, this is the perfect warmup event!
Kindly hosted by the awesome E.ON Digital Technology ✨
Program:
17:30 Venue opens
18:00 Talks: ~ 3 x 15 min
How AI fixed a terrible legacy codebase in 5 days with Ivett Ördög
The impact of genAI on development and the SDLC with Patrick Debois
Why you have to learn to eval your Coding Agents with Max Körbächer
19:00 Networking
20:30 THE END
Session Details
Ever noticed how AI agents shine on small projects but fall apart in large codebases? I think I know why. Despite the marketing hype, the effective context window of even the largest models is closer to 7–10K tokens. They do well when the codebase is small or modular — but quickly get stuck once complexity exceeds what they can manage. Worse, they lack the discipline to build modular code, so like undisciplined teams, they grind to a halt.
As a technical lead and coach, I’ve spent years helping engineers form habits that improve code quality while delivering features. So when I realized AI agents face similar struggles, I got curious: could we build workflows around them that mimic those habits?
That’s exactly what I’ve been working on. As a result, we finally tackled a project we’d postponed for years — and cut our operating costs by 70%. What took the AI five days would have taken us several months of engineering time.
In this talk, I’ll walk you through the setup, the practices behind it, and how you can apply them to make AI actually useful in your own messy, real-world codebases.
Ivett Ördög is a public speaker and the creator of Lean Developer Experience (aka Lean Poker), a gamified DevOps training tool that teaches agile, lean and continuous deployment practices to developers. She is based in Bavaria, Germany and has over 25 years of professional experience in software development and 15 in leadership. She is passionate about innovation, collaboration and learning, and enjoys sharing her knowledge and insights with others. She is also the creator and host of the @NextIncrement YouTube channel.
Development is experiencing a new phase of automation, similar to what we saw with DevOps. Numerous new tools are emerging, and it can be challenging to keep up with them. These tools, many empowered by agentic AI, are leading to new practices, and understanding the patterns of these practices will help you navigate the space of AI Native Development.
Patrick Debois 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.
You've got three coding assistants at your fingertips. ChatGPT just wrote beautiful Python that doesn't run. Claude nailed the algorithm but missed your coding style. Copilot autocomplete exactly what you were thinking—two hours ago. Sound familiar? Many developers today face the same dilemma: which AI actually makes you faster? Most of us just stick with whatever we tried first, or chase the latest model everyone's talking about on {Your favorite Social Media platform}.
But here's what I learned after testing various models after I suffered high frustration: the "best" AI isn't the one with the highest benchmark scores—it's the one that meshes with your codebase, your patterns, and your problems. This talk walks through the simple evaluation framework I built to stop guessing and start measuring. No complex MLOps setup required—just practical techniques to figure out which coding agent actually saves you time versus which one just feels impressive.
Max Körbächer is Founder and Technology Advisor at Liquid Reply. He is CNCF Ambassador, Linux Foundation Europe Advisory Board member and Founder and Emeritus Lead of the CNCF Environmental Sustainability TAG. Max focuses on platform engineering to simplify the current challenges of complex systems in the cloud native space and author of Platform Engineering for Architects. Besides, Max organizes Kubernetes Community Days in Munich & Ukraine, and Kubernetes & Cloud Native Meetup in Munich.
This event is brought to you as part of the AI Native Dev Community. Consider subscribing to the Mailing List, Podcast, and join our Discord Community