Kubernetes RCA and alerting using Gemini, Loki, Prometheus, Slack

by John Pranay Kumar Reddy ✓ · 178 views · created 2025-08-27 · AI Summarization, Multimodal AI

What this workflow does

This workflow has 26 nodes and runs on a schedule (every day). It uses only n8n's built-in nodes.

How it runs

Trigger: On a schedule (every day).

1. Loki (HTTP Request): calls an HTTP API
2. PromQL: Current endpoints (HTTP Request): calls an HTTP API
3. PromQL: Endpoints 5m ago (HTTP Request): calls an HTTP API
4. Pods Not Ready (HTTP Request): calls an HTTP API
5. CrashLoopBackOff (HTTP Request): calls an HTTP API
6. Pod Restart Spike (last 5m) (HTTP Request): calls an HTTP API
7. Pods Pending (HTTP Request): calls an HTTP API
8. SSH: uses SSH
9. Map Prometheus results into namespace/service (Code): runs custom JavaScript code
10. Map Prometheus results into namespace/service (Code): runs custom JavaScript code

…plus 15 more steps. See the full node list below.

Before you upgrade to n8n 3.0

Nodes used (6)

• Schedule Triggern8n-nodes-base.scheduleTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• SSHn8n-nodes-base.ssh
• Mergen8n-nodes-base.merge
• Ifn8n-nodes-base.if

From the author

Summary This n8n workflow automates Kubernetes root cause analysis (RCA) and incident alerting by integrating with Loki, Prometheus, and Slack. It streamlines log collection, cluster health monitoring, and AI-driven RCA with Gemini, saving DevOps teams hours…

View the original on n8n.io → Check your own copy