The flow
Starts it 2Model 2Logic 9Service 6
The steps in the order they run, from what starts it.
- 1Look For Flakes Each MorningSchedule triggerStarts it
- 2Or Run It NowManual triggerStarts it
- 3Flake ReaderLm Chat Open AiModel
- 4SettingsSetLogic
- 5Group The FailuresChain LlmModel
- 6Ask For The Recent RunsHttp RequestService
- 7Build The ReportCodeLogic
- 8Pick The Runs Worth ReadingCodeLogic
- 9Post The ReportSlackService
- 10Read The Jobs In Each RunHttp RequestService
- 11Score Every JobCodeLogic
- 12Read What You ReportedData TableService
- 13Only The New Or WorseCodeLogic
- 14Anything Random?IfLogic
- 15One Row Per JobCodeLogic
- 16One Issue Per Confirmed FlakeCodeLogic
- 17Nothing Random TodayNo OpLogic
- 18Remember What You ReportedData TableService
- 19Open An IssueGithubService
How it's built
- Starts on
- A clock
- Steps
- 19, with 1 branch
- Size
- Medium: a working afternoon
- Connects to
- GitHub, Slack, n8n data table
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own GitHub and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on a clock.
Does it use AI?
Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 19 steps is enough that you should read each one before running it.
How do I import it?
Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.
Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 19 steps before you point it at anything that matters.