Brian Haydin
Microsoft Cloud & AI Architect | Azure • GitHub • Power Platform | Demo-first sessions (US + Europe)
Milwaukee, Wisconsin, United States
Actions
I help teams modernize apps and platforms in the Microsoft ecosystem—Azure, GitHub, Power Platform, and identity (Microsoft Entra)—with a bias toward real-world constraints and practical outcomes. I’ve spent 20+ years building and advising solutions across manufacturing, healthcare, insurance, and financial services.
My sessions are story-driven and demo-heavy: less “cloud mythology,” more “here’s the pattern, here’s the pitfall, here’s the fix.” Recent topics include practical GPT/agent builds, Microsoft Fabric in real workloads, secure identity, and modern delivery pipelines.
Based in Milwaukee, available nationwide—and frequently in Europe (Nordics/Baltics, incl. Stockholm & Riga). I’m also the creator of the biweekly LinkedIn newsletter Tech Trekking, connecting emerging tech to what actually works in the field
Area of Expertise
Topics
AgentOps for Real: Observability, Evals, and Control for Production AI Agents
AI agents behave less like traditional software functions and more like probabilistic autonomous systems. They call tools, chain reasoning steps, and adapt their behavior based on model outputs, which means conventional testing and monitoring approaches break down quickly.
So how do engineering teams safely operate agents in production? How do you detect behavioral drift after model or prompt updates? Prevent silent regressions in tool-using agents? Debug complex multi-step executions? Monitor real-world behavior after deployment? And most importantly, how do you regain control when an agent starts going off the rails?
In this session, we’ll walk through a practical AgentOps lifecycle for production AI agents, including evaluation datasets, golden prompts, behavioral test suites, hybrid scoring methods, trace-driven debugging, regression testing for multi-step agents, CI/CD quality gates, and production monitoring and control patterns.
Using modern cloud tooling and .NET-based agent frameworks, we’ll explore repeatable techniques for testing, observing, and operating AI agents as real software systems; not magic. Attendees will leave with a practical framework they can apply to improve reliability, visibility, and control in their own agent-based solutions.
AgentOps for Real: Evals, Tracing, and Regression Tests for AI Agents on Azure
It's easy to build an AI agent demo in Azure. It's much harder to build one that stays reliable after prompt changes, model swaps, tool failures, and real user behavior start hitting it in production.
In this session, I'll show a practical AgentOps approach for Azure-based agents using evaluation datasets, golden tasks, tracing, telemetry, and regression testing. We'll walk through how to instrument an agent with observability using OpenTelemetry, Azure Monitor, and Application Insights - how to score responses with both rules and model-based judges, and how to catch regressions before they quietly torch trust in production. We'll also look at common failure modes in multi-step agent flows: tool misuse, hallucinated handoffs, brittle prompts, and silent drift after updates.
Built on Azure AI Foundry, Microsoft Agent Framework, and Azure Monitor, this session gives you a concrete playbook for moving from "cool prototype" to "production system people can actually depend on."
Three takeaways:
- Build an eval set that measures what your agent actually needs to do
- Add tracing and telemetry that make failures diagnosable
- Turn agent quality into a repeatable regression gate, not a vibe check
One Agent, Three Ways: Building a “Missed Meeting” Assistant in Low-Code, Pro-Code, and Hybrid
Ever built something in Copilot Studio and thought, “This is great—until it isn’t”? Or coded a Semantic Kernel agent and wondered if you just reinvented what a low-code builder could’ve done faster? In this session, we’ll follow a single use case—a personal “Missed Meeting” agent that summarizes what you missed and what to do next—and build it three different ways: Copilot Studio (low-code), Semantic Kernel + Azure AI (pro-code), and a hybrid approach that combines both.
You’ll see how the same idea flexes across environments: what’s easy, what’s limiting, and where each platform shines. Along the way, we’ll cover the real decision factors—data access, governance, extensibility, cost, and developer velocity—and wrap up with a framework for choosing the right path for your next agent. Whether you live in Power Automate or Visual Studio, you’ll leave knowing how to pick your build battles wisely.
The Cloud & AI Summit 2026 Sessionize Event Upcoming
Scenic City Summit 2026 Sessionize Event Upcoming
MN Microsoft 365 User Group - In person Workshop Day Spring 2026 Sessionize Event Upcoming
Chicago Global Azure 2026 Sessionize Event
Global AI Milwaukee AgentCamp 2026 Sessionize Event
Orlando Code Camp 2026 Sessionize Event
AgentOps for Real: Chippewa Valley Code Camp
AgentOps for Real: Evals, Tracing, and Regression Tests for AI Agents
Shipping an AI agent without observability is like deploying a distributed system with no logging. Learn how to implement evals, tracing, and regression testing so your agents don’t quietly degrade into chaos.
AI agents behave probabilistically — and that breaks traditional testing assumptions.
In this session, we’ll walk through a practical AgentOps stack.
We’ll implement examples using Azure-based tooling and .NET, including how to structure regression tests for multi-step tool-using agents.
You’ll leave with a repeatable pattern for treating agents like real software — not magic.
The State of AI 2026: Purpose Built AI & ML
AI is now a core IT responsibility—but not all approaches are created equal. In this session, we’ll break down the State of AI in 2026 and what it means for IT leaders responsible for scalability, security, and long-term value. Learn why purpose-built AI and machine learning are replacing one-size-fits-all solutions, where organizations are seeing real impact today, and what decisions matter most when designing AI that can be governed, integrated, and sustained. Attendees will leave with a clearer framework for evaluating AI initiatives and prioritizing what to build next.
Global AI Milwaukee AgentCon 2025 Sessionize Event
June Global AI Milwaukee User Group Meeting - Panel
AI Microsoft Build AI Roundup
Microsoft //BUILD 2025 overflowed with new AI toys: small language models, copilots everywhere, smarter dev tools, and a buffet of both cloud and local AI tools. But what’s worth your time? Our three-person panel of AI professionals have cherry-picked the top AI releases from //BUILD that we believe will bend the curve for developers and businesses this year. We’ll:
Break down the “why” – real-world impact,
Demos – quick, no-fluff walkthroughs,
Open the mics – audience questions and rapid-fire idea-swapping,
Whether you’re shipping production models, tinkering with copilots, or just trying to stay ahead of the buzz, you’ll leave with concrete next steps and a bigger peer network.
Milwaukee SPIN: No Code, No Problem: How BAs Can Steer the AI-Powered App Journey
Presentation to the local Software Process Improvement Network (SPIN)
Worried AI might axe your role as a business analyst? Think again.
In this hands-on session, you’ll discover how Microsoft Copilot Studio can turn your plain-language requirements into fully functional, data-driven applications—without writing a single line of code. No coding campouts, no developer detours.
Remember: *developers may wield the axe, but you chart the course, set the bearings, and know where the s’mores are stashed.* With Copilot Studio, your trail map becomes GPS.
You’ll learn how to:
* Craft effective prompts that bring business needs to life
* Quickly model data in Dataverse
* Rapidly prototype and test apps with real users
Whether you're defining requirements or guiding delivery, this session puts you at the heart of your organization’s AI-powered journey. Come ready to lead the next expedition.
WI .Net User Group - Best of Build
Microsoft Build Recap By Brian Haydin
Join us for an engaging discussion following the Microsoft Build conference in Seattle, where technology enthusiasts and industry professionals come together to explore the latest innovations and trends in the tech world. Microsoft Build has a rich history of showcasing groundbreaking technologies and inspiring developers to push the boundaries of what's possible.
This year, the main theme of Microsoft Build is "How will AI shape your future?" highlighting the pivotal role that artificial intelligence plays in shaping the future of technology and innovation.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top