What problem does it solve? Answering questions about Google Kubernetes Engine spending—such as which namespace or workload drives costs, or why a cluster bill is spiking—requires joining BigQuery billing exports with cluster metadata and live utilization data, which is tedious and error-prone to do manually. ## Core Features & Use Cases - BigQuery Billing Analysis: Provides ready-to-adapt Standard SQL templates for the GCP Billing Detailed Export to break down costs by project, cluster, namespace, and workload. - Cost Allocation Verification: Explains how to check and enable GKE Cost Allocation so namespace- and workload-level labels appear in billing data. - Utilization Diagnosis: Compares live resource usage (kubectl top) against pod requests to identify over-provisioning in Autopilot or idle nodes in Standard clusters. - Use Case: Ask "What is my most expensive namespace in cluster X over the last 30 days?" and receive a concrete bq query command plus an explanation of the pricing drivers behind the result. ## Quick Start Ask the assistant to analyze your GKE costs by providing your BigQuery billing export table path and the cluster or namespace you want to investigate.
