Raphael De Lio is an AI and Software Engineer at Redis with over eight years of experience spanning multiple industries and countries. He is passionate about distributed systems and specializes in Java, Kotlin, and building scalable, high-performance software with a growing focus on reliable, distributed agentic systems.
What drives him is bridging the gap between software engineering and AI engineering, bringing the hard-won knowledge of building distributed, scalable systems into the world of AI where those foundations are often missing but matter most.
Originally from Brazil, Raphael spent six years in Portugal before making the Netherlands his home, where he also helps organize the Dutch Kotlin User Group. He loves blending code, community, and creativity to help developers build better systems faster, and with a lot more fun along the way.
In this workshop, we’re going to explore how to build a multi-agent system from the ground up using Spring AI. You’ll learn how to get multiple agents working together — each with its own role, memory, and context — all inside a clean, production-ready architecture.
AGENDA
Throughout this interactive session, you’ll explore practical patterns and real-world challenges as you:
- Design and organize your agents: Learn how to structure a multi-agent system, define agent responsibilities, and establish clear communication flows.
- Manage agent context and state: Explore techniques for maintaining contextual memory, ensuring each agent operates with relevant and up-to-date information.
- Enable communication among sub-agents: Implement effective coordination strategies so agents can share insights, delegate tasks, and make collective decisions.
- Make it production-ready: Learn best practices for monitoring, scaling, and securing your multi-agent system to ensure reliability and performance in real-world environments.
This workshop is highly interactive and iterative. You’ll be building, testing, and refining as you go.
Bring your laptop and get ready to code alongside us!
Artificial intelligence does not need to copy the human brain to advance, yet cognitive science still offers useful guidance. As agentic applications grow, understanding how humans store and retrieve information can help us design agents that act with greater context and reliability.
This talk connects human memory to the practical challenges of building AI agents with memory. We will review the main types of memory in the brain, revisit a landmark case in neuroscience, and relate these ideas to how large language models process information. We will also look at the real difficulties of taking agents to production, where choosing what to store and how to retrieve it becomes the core challenge.
Participants will learn:
- How insights from cognitive science can guide agent design
- The key forms of human memory and their relevance to AI
- The main obstacles of deploying agents with memory in real systems
- How our work at Redis led to an open-source, production-ready agent memory server
- Practical ways to improve memory in AI agents
This session offers both conceptual clarity and concrete tools for building more capable agentic systems.
Searching for speaker images...