Posts

Cluster Doctor: Agentic Platform Engineering - Part 1

What does an AI agent that diagnoses Kubernetes cluster problems actually look like in practice? Part 1 of a two-part demo on the GBB channel.


Published on the Microsoft Global Black Belts YouTube channel.

Cluster Doctor is a demo I built to show what agentic platform engineering looks like beyond the toy examples. The agent takes a broken or degraded Kubernetes cluster, runs diagnostics, correlates signals across logs and metrics, and produces an actionable diagnosis - without a human manually triaging each layer.

Part 1 covers the core agent architecture and the initial diagnostic loop. Part 2 goes into configuration and tuning.

Watch on YouTube →