Sergi Almar Spring Sensei Building agents that actually work, ones that plan, reason, use tools, ask clarifying questions, and collaborate with other agents, requires more than just calling an LLM in a loop. It requires understanding agentic patterns and the protocols that connect them. In this talk, we'll build progressively more capable AI agents using Spring AI. We'll start with the fundamentals and tool calling. We'll then move into agentic territory, looking at workflow patterns and building autonomous agents with recursive advisors and composable skills. Finally, we'll cover the emerging agent protocol landscape: MCP for connecting agents to external tools and services, and A2A for enabling agents to discover and collaborate with each other. By the end of this talk, you'll have everything you need to build your own Claude Code-style agent.

Session Speakers

Sergi Almar

Independent Software Engineer