Building effective LLM-based applications with Semantic Kernel

While it may sound like LLMs and generative AI are more of a data science thing, they aren't. You, as a developer, can work with this technology too.

In this workshop, we'll help you build an RAG system from start to finish using Semantic Kernel while teaching you topics such as LLMOps, LLM Security, and various design patterns useful for building LLM-based applications.

By the end of the workshop, you'll know:

* How to build an agent with tools such as search
* How to deploy and maintain your agent
* How to secure your agent against various attacks
* How to apply various LLM design patterns

Platform engineering: making organizational, cultural and technical choices

This session explores key concepts of platform engineering, the responsibilities of platform and application teams, and the cultural dynamics essential for successful collaboration. Gain actionable insights from real-world examples to enhance your platform engineering practices. The speakers will share their practical experience with designing, building, and operating a standardized platform for running cloud-native applications.

Shift Left on Non-Functionals: Continuous Validation with Azure

Non-functional requirements like performance, scalability, and resiliency often get pushed to the end of development — a costly mistake that leads to late-stage firefighting, expensive rework, and unpredictable production issues.

This session flips the script by showing how to embed continuous validation of non-functional requirements early and throughout your development lifecycle. You’ll get hands-on guidance on leveraging Azure’s testing and monitoring ecosystem—from automated load testing and chaos experiments to telemetry-driven insights—that enable developers and architects to detect and fix problems before they escalate.

Through practical demos, real code snippets, and pipeline examples, you’ll learn how to own your system’s reliability and performance from day one, building resilient software that scales and performs under pressure. If you want to move beyond reactive fixes and deliver non-functional excellence continuously, this talk will give you the mindset and toolkit to get there.

.NET supply chain: Protecting against hidden threats

Modern software relies heavily on third-party components like open-source libraries and NuGet packages, which can introduce security risks. If you're not carefully managing these dependencies, you could expose your application to vulnerabilities or even malicious code—just like what happened with Log4J.

In this session, we'll cover best practices for securing your .NET projects, including using tools like Trivy and NuGet’s security features to scan and monitor dependencies. We’ll also discuss supply chain observability—how to track vulnerabilities and ensure the integrity of your components.

Beyond tools, we'll touch on team policies for approving third-party libraries, setting security gates in CI/CD pipelines, and fostering a security-first mindset in your organization. Live demos will show practical steps you can implement right away to protect your applications.

SLIs Are Not Metrics

Most systems today are over-instrumented and under-observed. You’ve got a dozen dashboards and a graveyard of alerts, but when things break, you’re still asking: “What just happened—and did users notice?”

This talk is about fixing that, starting with a simple idea: Service Level Indicators (SLIs) are not just metrics—they’re contracts between your system and your users. We’ll walk through building SLIs that actually reflect user experience, instrumenting them using OpenTelemetry, and wiring them into Azure’s Health Model to create a platform-native reliability feedback loop.

You’ll learn how to define meaningful indicators (not just what’s easy to measure), surface them in Azure Monitor, and use them to drive Service Level Objectives (SLOs), error budgets, and deployment gates. Along the way, we’ll discuss the anti-patterns that kill signal quality, how to avoid “observability theater,” and why developers—not just SREs—should own reliability from day one.

Expect strong opinions, live demos, and answers to questions most dashboards can’t.

Discover how to build meaningful Service Level Indicators (SLIs) using OpenTelemetry and Azure’s Health Model. This session dives into practical instrumentation, turning raw telemetry into actionable reliability signals, and integrating them into real-world SLOs and error budgets. Designed for developers who want to own reliability and move beyond noisy metrics to signals that truly matter.