The flow
Starts it 1Model 3Logic 7Service 7
The steps in the order they run, from what starts it.
- 1Start a pool runManual triggerStarts it
- 2Chat model for authoring and repairLm Chat Open AiModel
- 3Your brief and productSetLogic
- 4Your LLMChain LlmModel
- 5LLM (repair)Chain LlmModel
- 6Build authoring promptSpintaxService
- 7Validate draftSpintaxService
- 8Validate (attempt 2)SpintaxService
- 9Render 12 variantsSpintaxService
- 10Build repair promptSpintaxService
- 11Still invalid - stop (loop is capped)No OpLogic
- 12Twelve distinct documents?IfLogic
- 13Lint each variantSpintaxService
- 14Too few - the template cannot fill the poolNo OpLogic
- 15Check pool uniquenessSpintaxService
- 16Defective - droppedNo OpLogic
- 17Ready to publishNo OpLogic
- 18Dropped - too similarNo OpLogic
How it's built
- Starts on
- An event in a connected app
- Steps
- 18, with 1 branch
- 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 an event in a connected app.
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. 18 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 18 steps before you point it at anything that matters.