Remediate Kubernetes CrashLoopBackOff incidents with OpenAI, Slack, SendGrid and Google Sheets
Needs changesWhat this workflow does
This AI workflow has 32 nodes and runs when an HTTP POST request hits its webhook URL (plus 1 other trigger). Along the way it connects OpenAI Chat Model. It also calls hooks.slack.com, api.sendgrid.com and sheets.googleapis.com over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 1 other trigger).
- Fetch Kubernetes Pods Status (HTTP Request): calls an HTTP API
- Scan CrashLoopBackOff Pods (Code): runs custom JavaScript code
- If: checks a condition and branches into true / false
- Fetch Logs for Detected Pods (HTTP Request): calls an HTTP API
- Respond No CrashLoop Found (Respond to Webhook): sends the response back to the webhook caller
- Prepare Log Data for AI (Code): runs custom JavaScript code
- Log Analysis Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-4.1-Mini
- Parse AI Crash Diagnosis (Code): runs custom JavaScript code
- Route by AI Recommended Action (Switch): routes items into 4 branches
- Delete Pod to Restart (HTTP Request): calls an HTTP API (DELETE)
…plus 18 more steps. See the full node list below.
Services it uses
HTTP calls to: hooks.slack.com, api.sendgrid.com, sheets.googleapis.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Log Analysis Agent (v1.6), Incident Summary Agent (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Log Analysis Agent (v1.6), Incident Summary Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (11)
- Webhook
n8n-nodes-base.webhook - Schedule Trigger
n8n-nodes-base.scheduleTrigger - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - Respond to Webhook
n8n-nodes-base.respondToWebhook - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Switch
n8n-nodes-base.switch - Merge
n8n-nodes-base.merge - Wait
n8n-nodes-base.wait
From the author
Quick overview This workflow detects Kubernetes pods in CrashLoopBackOff via an Alertmanager webhook or a 2-minute poll, fetches failing container logs, uses OpenAI to diagnose the likely root cause and recommended remediation, applies the remediation through…