Walkthrough¶
Get started with HolmesGPT by running your first investigation.
Prerequisites¶
Before starting, ensure you have:
- ✅ HolmesGPT CLI installed - See CLI Installation Guide
- ✅ AI provider API key configured - See AI Provider Setup
- ✅ kubectl access to a Kubernetes cluster - Any cluster will work
Run Your First Investigation¶
Let's investigate a pod with HolmesGPT to see the value it provides:
-
Create a test pod with an issue:
-
Ask Holmes to investigate:
-
See the value: Holmes will analyze the pod, identify that it's stuck in "Pending" state due to an invalid node selector, and suggest specific remediation steps - all without you needing to manually run
kubectl describe
, check events, or dig through logs.
What You Just Experienced¶
HolmesGPT automatically:
- ✅ Gathered context - Retrieved pod status, events, and related information
- ✅ Identified the root cause - Invalid node selector preventing scheduling
- ✅ Provided actionable solutions - Specific commands to fix the issue
- ✅ Saved investigation time - No manual troubleshooting steps required
Clean Up¶
Remove the test pod:
Next Steps¶
- Add integrations - Connect monitoring tools like Prometheus, Grafana, and DataDog
- Troubleshooting guide - Common issues and solutions
- Join our Slack - Get help from the community
- Request features on GitHub - Suggest improvements or report bugs