Toronto Java Users Group

Choose Your Own AI Adventure
Java, agents, and rabbit holes. You choose.

AI can write a lot of code. Getting it to build what you actually meant—and knowing whether to trust the result—is where things get interesting.

In this choose-your-own-adventure talk, the audience decides which paths we explore in real time. Each choice takes us into a different part of building with AI and building AI into applications.

The possible paths include spec-driven development, LLMs, Java and Spring AI, security, the AI SDLC, token and cost optimization, evals, RAG, and LLM-as-judge. We’ll also explore practical workflows with Claude and Codex, voice brainstorming, and what “agentic” actually means once you look under the hood.

Expect practical examples, tips you can use the next day, honest tradeoffs, and a little 80s nostalgia. The talk itself is part of the experiment—an AI-built adventure that the room gets to steer.

Bring your questions. Choose your path. Let’s see where we end up.

About the venue
Free Times Cafe has bistro-style seating and a full food and drink menu. Please consider helping to support the venue by planning to have supper during the talk.

Speaker Bio
Victor Szoltysek is a seasoned consultant and technologist, currently at RAVL, where he helps clients eliminate the inefficiencies of undifferentiated heavy lifting and focus on building solutions that drive real business value for their customers. With a career spanning notable organizations like Accenture, Pivotal, and ThoughtWorks, as well as numerous startups, Victor brings a wealth of experience in cloud transformations, DevOps enablement, and Agile software development.

A dedicated Java enthusiast with a sharp eye for cutting-edge technologies, Victor’s work frequently intersects with AWS, where he strives to streamline workflows and help teams leverage the cloud without unnecessary complexity. Recently, he’s also ventured into the dynamic world of artificial intelligence, exploring ways to make programming more engaging, efficient, and rewarding.

Victor is known for his humorous and sometimes controversial presentation style, ensuring lively discussions and thought-provoking takeaways. His disdain for overly complex tech solutions drives his mission to simplify the way we build and deploy software. Whether he’s sharing insights about Java, AWS, or AI, Victor’s talks are as energizing and satisfying as your favorite cup of coffee. Don’t miss his unique blend of wit, wisdom, and deep technical expertise at our meetup!

** Note special location for this event: the IBM offices at 16 York Street, on the 7th Floor.**

Doors open at 6:00. Theresa Mammarella will be on site to sign guests in.

The talk will start at 6:30.

Topic

Building Intelligent Java Apps: Agent Patterns, MCP, and the Future of AI Native Design

As AI rapidly evolves from model experimentation to production-grade applications, Java developers are increasingly faced with a new paradigm: designing intelligent systems that can reason, interact, and adapt. This talk explores the emerging Java AI application development journey through the lens of agent-based architecture, with a focus on how the Model Context Protocol (MCP) and Agent2Agent (A2A) communication patterns are transforming the way we build intelligent, context-aware services. We’ll walk through the foundational shifts in building AI-native Java applications—moving beyond single-shot prompt-response interactions to multiagent coordination, persistent memory, and tool-augmented reasoning. We’ll also address the critical architectural trade-offs: performance versus flexibility, open source versus vendor-managed inference, local versus remote model deployment, and how to maintain security and observability in agent-based systems.

About the speaker
Daniel Oh

Java Champion, CNCF Ambassador & TAG DevEX Co-Chair, AAIF Ambassador, Microsoft MVP, Developer Advocate, Technical Marketing, Keynote Speaker, Published Author