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.
Most of us like to do local development. It means we’re in control of any dependencies, network issues/latency, configurations and cost. And we love to say that “It works on my machine” don’t we? 🙂
Now, with the advent of AI-driven development, it has become more challenging than ever before to do pure local development.
In this session we’ll take a look at various solutions to continue to do local, network-optional development, even with AI:
* Run AI models locally.
* Evaluate different code assistants that can work with these locally running models
* Explore how to infuse AI capabilities from local models into our code
* Compare models from different vendors; and with different sizes to find the right balance between performance and accuracy
* Weigh pros and cons of using local vs remote models
Come to this session to learn more about local development while leveraging AI to optimize our development flow, code and our functionality itself!
Developing AI applications today goes beyond simple single-model interactions. We're seeing a shift towards agentic AI systems, where multiple specialized agents work together, each capable of independent reasoning. While there’s a myriad of ‘low-code’, ‘citizen developer’, and vendor-backed solutions, the real challenge for an AI architect lies in effectively building, orchestrating, and deploying these custom, collaborative systems to production. Despite all the promises from “AI” vendors, actual custom software development and a robust deployment strategy are essential for success.
Given the diverse and complex tasks these systems handle, a "one-size-fits-all" approach to coordination just doesn't work. We'll explore the spectrum of agentic patterns, from reliable but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.
This talk will cover:
* The pros and cons of various agentic patterns.
* Practical demonstrations of how to combine these patterns using LangChain4j and its Quarkus extension.
* How to leverage the provided infrastructure for agent collaboration.
* The flexibility to implement and seamlessly integrate your own custom agentic patterns.
Searching for speaker images...