Mary Grygleski

Mary Grygleski

Java Champion

Mary is the VP 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 especially 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.

Presentations

Building Scalable Multi-Agentic AI Systems in Java with Event-Driven Approach

This talk will guide Java 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 Java frameworks and messaging protocols.

  • Introduction of Event-Driven concepts
  • Demystifying Agentic AI and Multi-Agentic Workflows for Enterprise-level systems
  • Important Data Streaming and Distributed Data concerns
  • Example of Building a Basic example of Data Pipeline to illustrate the use of Event Streaming for Agentic workflow
  • Challenges of today's AI Apps and GenAI systems

Orchestrating Intelligence: Multi-Agentic Design Patterns for Production AI

As generative AI systems evolve from single LLM calls to complex, goal‑driven workflows, multi‑agent architectures are becoming essential for robust, scalable, and explainable AI applications.

This talk presents a practical framework for designing and implementing multi‑agent generative AI systems, covering four core orchestration patterns that define how agents coordinate:

Orchestrator‑Worker: A central agent decomposes a task and delegates subtasks to specialized worker agents, then aggregates and validates results.

Hierarchical Agent: Agents are organized in layers (e.g., manager, specialist, executor), enabling abstraction, delegation, and error handling across levels.

Blackboard: Agents contribute to and react from a shared “blackboard” workspace, enabling loosely coupled, event‑driven collaboration.

Market‑Based: Agents act as autonomous participants that negotiate, bid, or compete for tasks and resources, useful in dynamic, resource‑constrained environments.

For each pattern, we show concrete use cases, such as customer support triage, research synthesis, code generation pipelines,  and discuss trade‑offs in latency, complexity, and observability.

Demystifying Generative AI

Everybody is talking about Generative AI and models that are better than anything else before. What are they really talking about?

In this workshop with some hands-on exercise, we will discuss Generative AI in theory and will also try it in practice (with free access to an Oracle LiveLab cloud session to learn about Vector Search).  You'll be able to understand what Generative AI is all about and how it can be used.

The content will include:

  • What is Generative AI?
  • What is LLM?
  • Interacting with LLM models
  • Prompt engineering
  • Vectors, embedding models and generating embeddings
  • Vector Search with Oracle Database 23ai
  • Understanding RAG (Retrieval Augmented Generation)

Demystifying Generative AI

Everybody is talking about Generative AI and models that are better than anything else before. What are they really talking about?

In this workshop with some hands-on exercise, we will discuss Generative AI in theory and will also try it in practice (with free access to an Oracle LiveLab cloud session to learn about Vector Search).  You'll be able to understand what Generative AI is all about and how it can be used.

The content will include:

  • What is Generative AI?
  • What is LLM?
  • Interacting with LLM models
  • Prompt engineering
  • Vectors, embedding models and generating embeddings
  • Vector Search with Oracle Database 23ai
  • Understanding RAG (Retrieval Augmented Generation)