Victoria Cheng

Specialized tools for managing the physical host server and systemd services. Use this to inspect CPU/Memory pressure, monitor core hub units, and query journal logs.

Specialized tools for network-level observability using Cilium and Hubble. Use this to investigate cluster-wide network flows, packet drops, and host-level networking without being restricted to a single namespace.

Specialized tools for inspecting the overall health of the Observability Hub platform. Use this for executive summaries and checking the health status of core platform components.

Specialized tools for managing Kubernetes pods within the Observability Hub. Use this for inspecting pod health, retrieving logs, and troubleshooting container-level issues.

Specialized tools for querying the LGTM stack (Thanos, Loki, Tempo) and performing automated incident investigations. Use this when the user asks to analyze metrics, search logs, retrieve traces, or run a full incident correlation.