Running Azure SRE Agent for AKS and Drasi Operations

This article presents a detailed technical blueprint for deploying an Azure SRE Agent tailored for AKS (Azure Kubernetes Service) and Drasi operations. It covers infrastructure deployment via Azure Developer CLI, custom subagents for incident triage and diagnostics, Azure Monitor response plans, scheduled health checks, MCP connectors for Microsoft Learn and Drasi docs, and fault-injection tests. The author explains the motivation behind building this pattern, including troubleshooting complex failure modes that span application runtime and platform reliability. The repository structure, agent design with four custom agents (drasi-incident-triage, aks-platform-diagnostics, drasi-runtime-diagnostics, and others), and deployment steps are outlined. This is a hands-on, technical guide for IT professionals working with Azure, AKS, and SRE practices.