Agentic Engineering & ToolingAgentic Engineering & Tooling
Conference40min
BEGINNER

Building Scalable Multi-Agentic AI Systems iwith Event-Driven Approach

A talk on building multi-agent generative AI systems with event-driven design. It covers agent collaboration, communication, memory, and workflow state using patterns like pub/sub, orchestrator, and supervisor, plus frameworks such as LangChain or Haystack, MCP interoperability, and streaming tools like Kafka or Pulsar for scalable, reliable messaging.

talk.summaryAiDisclaimer

Mary Grygleski
Mary GrygleskiLuMay AI
talks.description
This talk will guide developers through the design and implementation of multi-agent generative AI systems using event-driven principles. Attendees will learn how autonomous GenAI agents collaborate, communicate, and adapt in real-time workflows using modern frameworks (such as LangChain or Haystack) and messaging protocols.

Cover core patterns such as pub/sub, orchestrator, and supervisor for managing agent communication, memory, and workflow state. Discuss interoperability with MCP (Model Context Protocol) and how event streaming tools like Kafka, Pulsar, that can facilitate high throughput and reliability.
generativeai
event-driven
multi-agent
interoperability
talks.speakers
Mary Grygleski

Mary Grygleski

LuMay AI

United States of America

Mary Grygleski is the Sr. VP of AI Evangelism at LuMay AI focusing on Enterprise AI architecture and market expansion. She is also a Technical Advocate and Global VP of the Western Hemisphere at the AI Collective, a nonprofit AI community and think tank.

With 25+ years in software engineering and architecture, Mary has worked with organizations including IBM, Bank of America, and the Chicago Mercantile Exchange across Java, generative AI, cloud, and distributed systems. She is a frequent international speaker and an active community leader with the Chicago Java Users Group. Mary is also a Java Champion and Oracle ACE Associate.