This talk will discuss the core architectural patterns for introducing AI capabilities into an existing software system.
Imagine you are a music composer struggling to find inspiration for a pivotal movie scene. Then, you remember you are also a software engineer, and the solution becomes suddenly obvious. Join me in this session, where I will demonstrate how I enhanced my music composition process by harnessing the power of Spring Boot and AI.
This presentation will discuss the core architectural patterns for introducing AI capabilities into an existing software system, exploring concepts like templated prompts, agent tools, and integration of external knowledge. The Java ecosystem is getting more and more capabilities for building AI applications. But are they ready for production? Are there any gaps?
Throughout the session, I will build a composer assistant application using Spring Boot and an AI Orchestrator (Spring AI) to showcase how to make an LLM application production-ready. Is the developer experience affected when working locally with language models? How is observability different when it comes to tokens? Can we ensure resilience across the many integrations orchestrated by the AI? What strategies are available for deploying LLM applications?
In a final twist, you will choose which movie scene to score, and I'll compose and perform the music live for it, supported by AI. Will it meet the mark? There's only one way to find out: join me in exploring the practical side of AI applications, where Java and Generative AI offer tangible solutions to real-world use cases. Aaaaand action!
Thomas Vitale is a software engineer and architect specialized in building cloud native, resilient, and secure enterprise applications. Thomas designs and develops software solutions at Systematic, Denmark, where he's been working on modernizing platforms and applications for the cloud native world, focusing on developer experience and security.
