Skip to Content
View all events

Event-Driven Agentic Architecture

Published by O'Reilly Media, Inc.

Harnessing event-driven multi-agent architectures for complex workflows

What you’ll learn and how you can apply it

  • Understand event-driven concepts and apply its techniques to generative AI/LLM applications
  • Learn how to design generative AI applications and optimize using event streaming
  • Develop a basic generative AI multi-agentic application

Course description

Mary Grygleski, global VP for the western hemisphere at The AI Collective, guides developers through the design and implementation of multi-agent generative AI systems using event-driven principles. You’ll learn how autonomous GenAI agents collaborate, communicate, and adapt in real-time workflows using modern frameworks and messaging protocols. The course also covers core patterns such as pub/sub, orchestrator, and supervisor for managing agent communication, memory, and workflow state. You’ll also examine interoperability with the Model Context Protocol and how event streaming tools like Kafka, Pulsar, and Spring Messaging facilitate high throughput and reliability.

This live event is for you because...

  • You’re a software developer or software architect.
  • You work with generative AI and LLM applications.
  • You want to become an AI application architect or developer.

Prerequisites

  • Basic computer programming and system design knowledge

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Event-driven primer (15 minutes)

  • Presentation: Foundations of event-driven architecture—from producers to reactive systems
  • Group discussion: How does event-driven architecture differ from traditional request-response models in terms of scalability and decoupling?; What types of systems or business domains benefit most from an event-driven approach?
  • Hands-on exercise: Identify a few real-world systems (e.g., ecommerce, ride-sharing, IoT) and map out possible events, producers, and consumers
  • Q&A

Demystifying agentic AI and multi-agentic workflows (35 minutes)

  • Presentation: Agentic AI in practice—orchestration, autonomy, and enterprise patterns
  • Group discussion: What distinguishes an “agent” from a traditional service or microservice in enterprise systems?; When should you use multi-agent workflows instead of a single orchestrated pipeline?
  • Hands-on exercise: Sketch a simple multi-agent workflow for a business use case (e.g., customer support automation or document processing), identifying roles for at least three agents
  • Q&A
  • Break

Data streaming and distributed data concerns (30 minutes)

  • Presentation: Streaming data systems—consistency, latency, and network dependency
  • Group discussion: What are the trade-offs between event streaming platforms (e.g., Kafka, Pulsar) and traditional messaging queues?; How do concerns like schema evolution and event ordering impact downstream AI/agent behavior?
  • Hands-on exercise: Define an event schema for a streaming use case (e.g., user activity tracking), including key fields and versioning strategy
  • Q&A

Building a basic event-driven agentic data pipeline (40 minutes)

  • Presentation: Designing an event-driven pipeline for agentic workflows Group discussion: Where should intelligence (agents) live in a data pipeline, at ingestion, processing, or orchestration layers?; How can event streams trigger agent collaboration in real time?
  • Hands-on exercise: Design a simple pipeline—event producer → event broker → agent(s) → output system; include tools (e.g., Kafka, Spring Boot, Python or Java agents) and define event flow; each agent should be interacting with an LLM
  • Q&A

Your Instructor

  • Mary Grygleski

    Mary Grygleski is the vice president of Global for the Western Hemisphere at the AI Collective, overseeing the health and growth of the community in North and Latin Americas. She started her career in software engineering and has deep interest in distributed systems, which cover all spectrums in the computing world. She is also very passionate about tech advocacy and community work, and has been leading the Java users group in Chicago since 2015. She is recognized as a Java Champion and an Oracle ACE Associate.

Skill covered

Generative AI