The flow
Starts it 1Model 4Logic 6Service 9
The steps in the order they run, from what starts it.
- 1Chat inputChat triggerStarts it
- 2list deploymentsHttp RequestService
- 3Get memory for current sessionData TableService
- 4Code in JavaScript1CodeLogic
- 5Prepare Chat Prompt with MemoryCodeLogic
- 6HTTP RequestHttp RequestService
- 7Generate Image PromptOpen AiModel
- 8Generate an image1Google GeminiModel
- 9Convert Image to Base64Extract From FileService
- 10Format Image as Data URISetLogic
- 11Upload Image to CloudinaryHttp RequestService
- 12Return Hero Image URLCodeLogic
- 13Generate HTML (OpenAI)Open AiModel
- 14Save HTML to Memory TableData TableService
- 15Prepare Vercel Deployment PayloadFunctionLogic
- 16Deploy to VercelHttp RequestService
- 17Fetch Latest Deployment URL1Http RequestService
- 18Make Deployment URL PublicHttp RequestService
- 19Format Deployment URLSetLogic
- 20Respond to ChatChatModel
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 20
- Size
- Medium: a working afternoon
- Connects to
- n8n data table
- Model
- Gemini, OpenAI
Questions
What does it need to run?
An n8n account, and a key for Gemini and 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 Gemini and 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.
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 20 steps before you point it at anything that matters.