Find and track flaky CI jobs in GitHub Actions with OpenAI and Slack

by Daniel Shashko ✓ · 3 views · created 2026-09-02

What this workflow does

This AI workflow has 19 nodes and runs on a schedule (every day at 08:00) (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Slack and GitHub.

How it runs

Trigger: On a schedule (every day at 08:00) (plus 1 other trigger).

1. Settings (Edit Fields (Set)): sets 10 fields: owner, repo, workflow_name…
2. Ask For The Recent Runs (HTTP Request): calls an HTTP API (GET)
3. Pick The Runs Worth Reading (Code): runs custom JavaScript code
4. Read The Jobs In Each Run (HTTP Request): calls an HTTP API (GET)
5. Score Every Job (Code): runs custom JavaScript code
6. Read What You Reported (Data table): get
7. Only The New Or Worse (Code): runs custom JavaScript code
8. Anything Random? (If): checks a condition and branches into true / false
9. One Row Per Job (Code): runs custom JavaScript code
10. Group The Failures (Basic LLM Chain): sends a prompt to an LLM, with model: Flake Reader

…plus 5 more steps. See the full node list below.

Services it uses

OpenAI Chat ModelSlackGitHub

Before you upgrade to n8n 3.0

Nodes used (12)

• Schedule Triggern8n-nodes-base.scheduleTrigger
• Manual Triggern8n-nodes-base.manualTrigger
• Edit Fields (Set)n8n-nodes-base.set
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Data tablen8n-nodes-base.dataTable
• Ifn8n-nodes-base.if
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Slackn8n-nodes-base.slack
• No Operation, do nothingn8n-nodes-base.noOp
• GitHubn8n-nodes-base.github

From the author

Quick Overview This workflow runs daily (or on demand) to analyze GitHub Actions re-runs for a specific workflow and branch, identify flaky jobs by comparing pass/fail history across attempts, summarize likely causes with OpenAI, post a report to Slack, file…

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