Prompting your platform: Building AI Powered infrastructure templates

More organizations are adopting infrastructure templates to streamline the creation of secure, compliant applications. In this session, you’ll discover how to build MCP (model context protocol) servers and design AI agents that interact with these templates, helping your developer teams with picking the right infrastructure components. See how GitHub and Kubernetes MCP servers can work together to drive GitOps-powered automation in Azure.

This talk is for platform engineers and developers building cloud infrastructure. Expect hands-on demos to help you use AI to automate.

Introduction to evaluating generative AI applications

Demos are easy; dependable AI is not. This session shows how to verify that your LLM apps actually work using Azure AI Foundry and Microsoft's agent framework. We’ll cover what to measure and how to spot and reduce hallucinations with groundedness checks. You’ll see evaluators in action, and learn how to continuously evaluate your AI applications to ensure the quality of the outputs remains up to par across releases.

Context Engineering: The Missing Discipline for Reliable AI Agents

If you have used an LLM agent, you probably have noticed that at the start of a new conversation the agent is smart, helpful and to the point. But as the conversation goes on it starts to make more and more silly mistakes, forgets important facts, or even gets stuck entirely. This 'context rot' is inherent to how LLMs work, but production AI agents must be able to remember key information and not go off the rails when working on a bigger task. So how do we make our agents more reliable?

This session introduces Context Engineering as an evolution of prompt engineering: the discipline of dynamically constructing the right context at the right time across an agent’s lifecycle.

In this session, you will learn how to practice Context Engineering by writing, selecting, compressing, and isolating information to keep agents accurate and stable over time. The session will also cover how to design agent memory, combining short-term state with long-term memory using patterns like rolling summaries and structured user profiles.

Building Cloud Native Applications with WebAssembly System Interface

The WebAssembly System Interface (WASI) is revolutionizing the world of cloud computing as we know it. You might have heard that it has the potential to replace containers, but how does it work? How do you get started? And how do you build a real application with WASI?

In this talk, we will dive into what WebAssembly and WASI are and how to develop applications that use this new technology. Additionally, you will learn about several projects in the WASI ecosystem that can help accelerate your WASI development journey.

By the end of this talk, you will not only have a strong understanding of WASI and its capabilities, but also the knowledge and tools to begin solving real-world problems with this cutting-edge technology. If you are curious about WASI and what it can do for your applications, this is the talk for you!

target audience: beginning WASI developers

GitOps in Action: Managing Azure Infrastructure with ArgoCD & Azure Service Operator

In this session, explore the world of GitOps and learn how to automate and manage your Azure infrastructure using kubernetes, ArgoCD, and the Azure Service Operator. We'll walk you through syncing your cloud resources directly from declarative configuration stored in a Git repository, combining the power of infrastructure-as-code with the simplicity and familiarity of Git workflows.

This talk is perfect for developers, DevOps engineers, and platform engineers looking to expand their horizons past ci/cd pipelines. Expect hands-on demos and practical guidance to get started with deploying and managing Azure infrastructure like a pro.