Building Smarter Java AI Agents with Embabel

Rod will give us a code-first, hands-on introduction to Embabel, a powerful agent framework for the JVM that helps Java developers build GenAI applications with greater structure, predictability, and control. This session goes beyond hype and demos to show how Embabel’s deterministic planning model makes AI workflows easier to reason about, test, and integrate into real-world systems. You’ll see how its elegant, consistent API supports multiple LLMs in the same workflow, how agentic RAG improves on older pipeline-based approaches, and how Embabel connects naturally with your existing domain model, business logic, and MCP integrations. If you want to understand how to build production-ready AI workflows in Java without sacrificing architectural discipline, this is a session you will not want to miss.

Streaming RAG and Real-time Ingestion

RAG is now the default pattern for enterprise AI. But most implementations are a patchwork of batch embedding jobs, external vector databases, message brokers, miscellaneous services, and brittle glue code. The result is predictable: higher latency, tougher and more costly operations.

In this talk, you’ll see a streaming RAG architecture built natively in Java: continuous ingestion and transformation with distributed DAG pipelines, horizontally scalable embedding inference, and in-memory distributed vector collections for millisecond semantic search. We’ll show how data can be vectorized as it arrives from CDC, events, REST sources, and documents, how partition-aware processing cuts network overhead, and how co-locating compute with vector storage enables fast retrieval with filtering and enrichment in a single runtime. The goal is a unified, stateful platform that reduces architectural sprawl while improving latency and resilience.

Joe Sherwin is a Principal Solution Architect at Hazelcast with 22 years of experience in the design, development, and implementation of application systems within multi-tier distributed computing environments.