Build a Platform Agent on Azure with Azure OpenAI and Azure MCP Server

🛠 Lab from the AI Platform Engineering on Azure course. Doubles as the Azure-variant slot for the AI Platform Engineering Bootcamp Week 4. Course landing page: https://academy.tekanaid.com/courses/ai-platform-engineering-azure Bootcamp landing page: https://academy.tekanaid.com/bootcamps/ai-platform-engineering-bootcamp

🟡 Beta lab. Hands-on instructions, check scripts, and solve scripts are in place.

This lab is your end-to-end introduction to the Azure-native agent stack. You will provision a real Azure OpenAI resource and deploy a `gpt-4o-mini` model, scaffold a C# ReAct agent with the Microsoft Agent Framework 1.6.1 package set, attach the Microsoft-first-party Azure MCP Server so the agent can answer questions like "what resource groups do I have?" by calling Azure's management plane, containerize and deploy the agent to AKS using ACR admin credentials for image pull and an AOAI API key Kubernetes Secret, and wire Application Insights so every think-act-observe step shows up as a trace. By the end you will have shipped the Azure-flavored version of the bootcamp's `ai-platform-assistant` pattern with the four Azure-specific building blocks: Azure OpenAI model, Azure MCP Server tools, AKS deployment, and Application Insights observability.