AI systems are moving beyond single-model architectures. The future is multi-agent — where multiple specialized agents collaborate, share context, and make decisions together. In this talk, we’ll explore how to build a multi-agent system using Spring AI, from design principles to production readiness.

You’ll learn how to design agents with clear roles, manage their memory and context, and enable communication between sub-agents so they can coordinate and solve complex tasks as a team. We’ll also cover how to organize your code for maintainability and how to scale your setup for real-world use.

By the end of this session, you’ll have a clear picture of what it takes to move from a single-agent prototype to a robust, production-grade multi-agent architecture using the power of the Spring ecosystem.