Agents Lookup

Use cases / IT & DevOps

Kubernetes troubleshooting with read-only cluster access

An agent inspects pods, events and logs to explain why a workload is failing and suggests fixes for an engineer to apply.

DifficultyIntermediate
Setup time1-2 hours
CategoryIT & DevOps

The use case

Kubernetes failures like CrashLoopBackOff, pending pods or failed probes take time to diagnose, especially for engineers who do not live in the cluster. Open-source tools HolmesGPT and K8sGPT read cluster state, events and logs and explain the likely cause in plain language with suggested fixes. Anthropic's data infrastructure team described using Claude Code to diagnose a cluster that stopped scheduling pods. Give these tools read-only access. An engineer still checks the explanation, applies fixes through the normal GitOps or change process, and keeps write access away from the agent.

Example workflow

  1. Install the tool with a read-only service account
  2. Point it at the failing namespace or workload
  3. Read the explanation and suggested fixes
  4. Verify with kubectl and logs
  5. Apply the fix through your usual deployment process

Tools

Risks and guardrails

Sources

Written by Agents Lookup. Credits and official pages for the tools this use case names: