Agents Talking to Agents: Inside the A2A Protocol

Real-world problems need specialists working together. The same is true for AI agents: it’s better to have a set of niche experts than a single mind that’s mediocre at everything.
But that raises a new question: how do those agents communicate effectively?

In this session, we introduce the Agent-to-Agent (A2A) protocol, an open protocol designed to let autonomous agents discover each other, exchange tasks, stream progress, and collaborate across frameworks and languages.

We’ll explain why A2A exists, what problems it solves compared to framework-specific agent integrations, and then go inside the protocol, covering concepts like agent cards, tasks, sessions, and event-driven execution.

AI Gateway : how to securely manage and scale generative AI workloads.

AI services are primarily accessed through APIs, highlighting the critical importance of a robust and efficient API management strategy. This strategy is vital for maintaining control and governance over the consumption of AI services.

As AI services continue to expand and seamlessly integrate with APIs, there is a growing demand for a comprehensive AI Gateway concept. This concept extends the core principles of API management, aiming to accelerate the experimentation of advanced use cases and pave the way for further innovation.

In this session we will present the AI Gateway concept and the APIM capabilities to implement different design patterns.

Healthy apps, happy users: smarter monitoring with Azure Health Models

Traditional monitoring gives us plenty of metrics, dashboards, and alerts but it doesn’t always tell us what we really need to know: is my application healthy for the end user?

In this session, we’ll dive into Azure Monitor Health Models (preview), a new capability that bridges the gap between raw telemetry and business context. You’ll learn how to define health based on your critical business flows (e.g., login, checkout, live data feed), map them to the technical components and dependencies that support them, and configure signals that reflect what “healthy” really means for your application.

You’ll see how Health Models drastically simplify monitoring, cut down alert fatigue, and provide a clear, aggregated view of your system’s resilience all while keeping the focus on what matters most: your customers’ experience

Cut the Noise: Alert on What Really Matters with Azure Health Models

Building declarative AI agents, the cloud-native way

LLMs are no longer just conversational engines, they’ve become the foundation for autonomous agents that can act, reason over tools and APIs, and work alongside other agents. But despite this progress, many AI agent frameworks still aren’t built to run natively on Kubernetes.

In this talk , we explore how to build declarative AI agents the cloud-native way, treating agents as first-class platform resources on Kubernetes. You’ll see how kagent, a CNCF sandbox project, enables platform teams to define, run, and govern agents using familiar Kubernetes patterns bringing structure, observability, and scalability to agent-based systems.