The CLI Agent for AKS brings an AI troubleshooting loop directly into az so operators can ask natural-language questions (e.g., “why is my pod Pending?”) and get grounded reasoning, targeted diagnostics, and safe, human-in-the-loop remediation steps—without leaving the terminal. It’s built on open source (HolmesGPT + AKS-MCP), runs locally with your Azure RBAC, and is extensible via runbooks and MCP toolsets. In this demo we will go through how to get started with CLI agent for AKS and AKS MCP server, some complex networking issue troubleshooting using "az aks agent" and share how you can get involved in the community.

Why this matters (3 takeaways)
- Cut MTTR: Turn scattered logs/metrics into concise RCA with actionable next steps.
- Secure by design: Local execution + Azure CLI auth; no cluster changes without explicit approval.
- Composable & open: Plug in your AI provider, observability stack, and MCP tools/runbooks as “lego blocks". Enabling the community to contribute.