Efstratios (Stratos) is an Upper Senior Software Engineer building large-scale data platforms and AI systems. He architects data infrastructure and leads MLOps initiatives, with expertise in platform engineering and data architecture. At Agile Actors, he engineers data solutions while mentoring teams in software development practices. His technical interests include distributed systems, compiler design, and quantum computing.
In the race to build AI-powered applications, we often overlook the power of simplicity. Through working examples, we'll explore how effective LLM integrations can be built using basic, composable patterns rather than complex frameworks. We'll demonstrate real-world implementations using minimal dependencies, showing how to create reliable systems while avoiding common pitfalls.
What you'll learn? When to use different patterns (workflows vs. agents), how to design clean interfaces, and most importantly, when to keep it simple versus when to add complexity. By the end, you'll have a clear understanding of how to build LLM-powered systems that are maintainable, scalable, and actually work in production.
Searching for speaker images...