The flow
Starts it 1Model 6Logic 8Service 5
The steps in the order they run, from what starts it.
- 1GH - Get PRGithubService
- 2Get FilesGithub ToolService
- 3Structured Output ParserOutput Parser StructuredModel
- 4Get RepoGithub ToolService
- 5o3-miniLm Chat Open AiModel
- 6gpt4.1-miniLm Chat Open AiModel
- 7WebhookWebhookStarts it
- 82nd Node for TestingCodeLogic
- 9Structured Output Parser1Output Parser StructuredModel
- 10Test MakerAgentModel
- 11Code ReviewerAgentModel
- 12Extrat API URL, owner and repoCodeLogic
- 13MergeMergeLogic
- 14GET .diff fileHttp RequestService
- 15Merge info neededMergeLogic
- 16Prepare for POSTCodeLogic
- 17Splits text into arrayCodeLogic
- 18Get File nameCodeLogic
- 19POST CommentsHttp RequestService
- 20FIlter for componentsCodeLogic
How it's built
- Starts on
- Another system calling it
- Steps
- 20
- Size
- Medium: a working afternoon
- Connects to
- GitHub
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own GitHub account, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on another system calling it.
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. 20 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 20 steps before you point it at anything that matters.