Self-heal web app outages with Claude, GitHub and Slack
Ready for 3.0What this workflow does
This workflow has 24 nodes and runs on a schedule (every 2 minutes). It uses only n8n's built-in nodes. It also calls api.anthropic.com and hooks.slack.com over HTTP.
How it runs
Trigger: On a schedule (every 2 minutes).
- Set - Config (Edit Fields (Set)): sets 8 fields: healthCheckUrl, expectedStatusCode, githubOwner…
- HTTP Request: calls an HTTP API
- JS - Evaluate Health Result (Code): runs custom JavaScript code
- If: checks a condition and branches into true / false
- HTTP Request: calls an HTTP API
- HTTP Request: calls an HTTP API
- JS - Identify Likely Changed Files (Code): runs custom JavaScript code
- Split Out: splits a list into separate items
- HTTP Request: calls an HTTP API
- Aggregate: combines items into one
…plus 12 more steps. See the full node list below.
HTTP calls to: api.anthropic.com, hooks.slack.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (8)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - No Operation, do nothing
n8n-nodes-base.noOp - Split Out
n8n-nodes-base.splitOut - Aggregate
n8n-nodes-base.aggregate
From the author
Quick overview This workflow runs on a schedule to health-check a web app, and when it detects an outage it gathers recent GitHub context and source files, asks Anthropic Claude to propose a fix, then creates a GitHub branch and pull request and notifies…