Architecting Autonomy: Building and Testing Agentic LLM Workflows

Agentic AI systems promise to go beyond simple prompts and responses—designing workflows where large language models act, adapt, and deliver. But how do we actually build them with reliability in mind?

In this session, we’ll walk through the foundations of architecting agentic workflows: from understanding Model Context Protocol (MCP) and AI tooling, to choosing workflow orchestration tools and weighing their trade-offs. We’ll explore strategies for testing—both deterministic tests where possible, and flexible testing frameworks where unpredictability is the rule. Finally, we’ll dive into how these tests guide iteration toward robust, production-ready agentic systems.

Grounded in real-world experience building AI at a rapidly growing tech company, this talk is designed as an introduction for engineers and curious builders alike. No coding is required, but attendees will leave with a clear mental model of how agentic workflows are structured, tested, and improved—and a practical toolkit to begin designing systems that build and iterate reliably, all on their own.

Intended as 1 hour session, can be adapted

Baby's first MCP: Build a Model Context Protocol From Scratch

An hands-on workshop where you'll build a production-ready MCP server from scratch. As a fill stack engineer who builds and maintains these systems daily, I'll teach you the patterns that actually work in production environments and how to integrate with tools like Claude Code, and custom servers.

Participants will:
- Build a real MCP server with proper error handling, authentication, and performance considerations
- Learn production patterns from someone who debugs integration issues and scales these systems professionally
- Avoid common pitfalls through practical insights you won't find in documentation

Prerequisites: Basic programming experience. Laptop required. The first half of this workshop will interface with Claude Desktop which is not yet available on Linux, so Mac or Windows is recommended.

Outcome: Working MCP server you can deploy and extend for real projects.

When Matter Starts to Matter: What Thread and Matter mean for the future of IoT

If you’ve ever wrestled with smart device compatibility and thought, why is this still so hard?—you’re not alone. Matter and Thread promise to fix that, creating a more unified, reliable IoT ecosystem. But what do these standards actually mean for developers, and how do you prepare for what’s next?

This session breaks down Matter and Thread. We’ll cover:
- What they are and why they matter (haha, get it?) — A clear, practical look at how these standards work and what they solve.
- Implementation without the headache — What your team needs to know to support Matter and Thread in real products.
- Lessons from the trenches — The real-world challenges (and wins) we’ve encountered while preparing to adopt these standards.
- What’s next? — How Matter and Thread might evolve and what that means for IoT development.

If you're working in connected tech, this session will give you a preview of the state of mesh networking and what you need to know today to continue building connected tech at scale as we navigate the newest trends.

You Can Spell Manufacturing Without Data: How we built insight into the lifecycle of our products

We’ve been making things without data insights for centuries—pyramids, cathedrals, entire industrial revolutions. But trial and error isn’t exactly a competitive strategy anymore. To stay ahead, modern manufacturing needs more than just efficient assembly lines—it needs systems that collect, analyze, and act on data at every step.

In this session, we’ll break down:
- Integrating data pipelines — How to connect manufacturing processes without disrupting operations.
- Making data useful — Strategies for transforming raw production data into actionable insights.
- Predictive strategies — Using real-time analytics to identify and prevent issues before they escalate.
- Lessons from real-world builds — What worked, what failed, and the systems we refined along the way.

If you're building or optimizing data systems in manufacturing (or any industry with complex processes), this talk will give you practical tools and strategies based on my team's experience across our many manufacturing businesses.