Konferenzprogramm
Why Vibe-Coding Fails (And How to Fix It)
You tried GitHub Copilot, ChatGPT, Claude, but got messy code and frustrated teams. The problem isn't AI, it's the approach. Most developers 'vibe code': throwing random prompts hoping for magic. Others use rigid workflows with predefined steps. True agentic engineering uses feedback loops: agents evaluate outcomes and decide their next actions dynamically. In this live demo, I'll build a feature inside a legacy app with a coding agent that analyzes context, proposes solutions, and iterates based on test results. Delivering fast with quality.
Target Audience: Senior developers, tech leads, CTOs, and engineering managers
Prerequisites:none
Level: Introductory
Extended Abstract:
You tried GitHub Copilot, ChatGPT, even Claude. But instead of productivity gains, you got messy code and frustrated teams.
The problem isn't the AI, it's the approach. Most developers are 'vibe coding': throwing random prompts at AI hoping for magic. That's not agentic engineering.
In this live demo, I'll code a real feature in half the usual time, showing what separates vibe-coding from professional agentic engineering. You'll see how treating AI as a co-worker is just the beginning. The real power comes from teaching AI your architecture patterns and engineering practices.
Engineers will discover why their AI attempts felt frustrating and master techniques to make AI accelerate their work. CTOs will learn to guide their teams from AI-skeptics to engineers who ship 50% faster without sacrificing quality. Time to stop experimenting and start delivering. The magic is real, it's just been buried under bad practices.
Benedikt Stemmildt is an Agentic Software Engineering Advocate with 20+ years enterprise experience who helps CTOs overcome frustrated developers struggling with AI assistants. Having led 70+ developers at companies like OTTO, Breuninger, and BLUME 2000, he transforms AI frustration into reliable productivity through context engineering methodologies that achieve 10x efficiency improvements while preserving programming joy.
Vortrag Teilen
Redefining Agile Value Creation in the AI-Generated Code Era
As AI transforms software development, many foresee the demise of traditional programming and, with it, the Agile methodology. We think they are wrong. We'll look at why the Agile Manifesto's principles are more important than ever, not in spite of, but because of, artificial intelligence. Using real-world examples and emerging best practices, we'll look at how top firms are redefining value generation, team performance, and leadership in an AI-augmented development environment.
Target Audience: Decision Makers, Project Leads, Developers
Prerequisites:none
Level: Introductory
Principal AI Strategist
As a Principal AI Strategist at Amazon, Zorina Alliata leverages her expertise in AI and Generative AI strategy and product management to help global customers use AWS AI/ML products and services to speed up their operations and enhance their processes. She teaches the Responsible AI and Data Science courses at OPIT and Georgetown University. She is a certified AWS Solutions Architect, SAFe SPC, PMP. She is also a PhD candidate researching AI in Finance.
Dylan Alliata is a Senior Scrum Master in FINTECH and Program Manager with 15+ years of experience leading large-scale Agile transformations and technology projects across finance, insurance, and healthcare sectors. He specializes in scaling Agile frameworks such as Scrum and SAFe to optimize team performance, enhance delivery efficiency, and streamline cloud migrations. As a Senior Agile Instructor, he creates and delivers targeted training for professionals to improve Agile adoption and team performance.
Vortrag Teilen