About this talk
This session explores the maturation of Java GenAI libraries and how they simplify the integration of models like GPT and Gemini into applications. The speaker addresses the limitations of default configurations in quick prototypes, emphasizing the need for more robust enterprise implementations. Attendees will learn to take full control of execution flow, enhancing observability and predictability when AI interacts with internal data and tools. The talk also covers essential production requirements, focusing on security, identity-awareness, and Human-In-The-Loop (HITL) workflows, as well as strategies to secure the Model Context Protocol (MCP) and validate high-stakes operations.
More from this event
See all 29 talks →
Agents With Seatbelts: Practical Ways to Keep AI Code Gen Under Control, Jonathan Vila López
41:46
Practical MCP Security in Action, Willem Jan Glerum
43:59
Kotlin for Normal Brains (Without Jets), Nayden Gochev
59:30
Beyond the LLM API - What Developers Actually Need to Know About ML, Milen Dyankov
54:58