Kevin Dubois is a software architect and platform engineer with a career spanning over 20 years. He is often featured as a keynote speaker at conferences around the world where he shares his experience and knowledge about cloud native & AI software development, developer experience, open source and Java. Kevin is also an author and Java Champion. He currently works as a Senior Principal Developer Advocate at IBM, and is also Technical Lead for the CNCF Developer Experience Technical Advisory Group.
There is no universally agreed definition of what an AI agent is. In practice though, several patterns are emerging. These patterns demonstrate the coordination and integration of multiple AI services to build sophisticated Agentic AI systems capable of handling intricate tasks.
These Agentic Systems architectures can be grouped in 2 main categories: workflows, where LLMs and tools are orchestrated through predefined code paths, and autonomous agents, where LLMs dynamically direct their own processes and tool usage, maintaining control over how they execute tasks.
The goal of this talk is to give a theoretical overview of Agentic AI in general and these patterns in particular. We will discuss their differences and range of applicability and show with practical examples how they can be easily implemented and tested. We’ll use Quarkus and its LangChain4j extension, but the concepts are universal.
The last few months have seen the rapid evolution of LLMs from passive completion engines, only good for generic chatbots, to components of a more complex, programmatically defined, workflow and finally into active and autonomous elements capable of reasoning, planning, and taking actions.
But moving from basic prompt engineering to truly autonomous systems requires a new class of design patterns and possibly a framework allowing to implement those patterns and put them at work in a convenient and effortless way.
In this workshop, we will explore the architecture and implementation of agentic AI using LangChain4j, a Java-native framework for building LLM-powered applications. You’ll learn how to move beyond the plain usage of a standalone LLM to design intelligent, modular agents capable of dynamic decision-making, memory retention, tool usage, RAG, MCP and A2A integration and multi-step goal execution.
After having covered the core concepts of agentic AI, we will guide you in incrementally building and testing an agentic system from scratch using LangChain4j and Quarkus, backed by real-world examples and live coding. Whether you're exploring agentic AI for task automation, intelligent assistants, or decision-support systems, this session will give you the practical tools and architectural understanding to build robust and maintainable autonomous agents in Java.
Searching for speaker images...