The flow
Starts it 1Model 2Logic 9Service 3
The steps in the order they run, from what starts it.
- 1When chat message receivedChat triggerStarts it
- 2OpenAI ModelLm Chat Open AiModel
- 3Parse PR URLCodeLogic
- 4AI Code Review AgentAgentModel
- 5Has Error?IfLogic
- 6Send Review ResponseNo OpLogic
- 7Send Error MessageNo OpLogic
- 8Get PR DetailsHttp RequestService
- 9Format Review OutputCodeLogic
- 10Get Changed FilesHttp RequestService
- 11Post to GitHub?IfLogic
- 12Prepare AI ContextCodeLogic
- 13Post Review to GitHubHttp RequestService
- 14Skip PostingCodeLogic
- 15Post Success MessageCodeLogic
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 15, with 2 branches
- Size
- Medium: a working afternoon
- Connects to
- Nothing by connector; it calls services over plain HTTP
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on someone opening a chat with 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. 15 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.
Before you run itNothing 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 15 steps before you point it at anything that matters.