The flow
Starts it 1Model 7Logic 2Service 1
The steps in the order they run, from what starts it.
- 1Gmail triggerGmail triggerStarts it
- 2OpenAI GPT-4oLm Chat Open AiModel
- 3Parser ResultOutput Parser StructuredModel
- 4OpenAI GPT 4o - For EnglishLm Chat Open AiModel
- 5OpenAI GPT-4o - for JapaneseLm Chat Open AiModel
- 6Assess if a message needs a reply and identify the languageChain LlmModel
- 7Generate email reply for an English clientChain LlmModel
- 8Generate email for a Japanese clientChain LlmModel
- 9If Needs ReplyIfLogic
- 10Gmail - Create DraftGmailService
- 11Switch based on email languageSwitchLogic
How it's built
- Starts on
- An arriving email
- Steps
- 11, with 2 branches
- Size
- Medium: a working afternoon
- Connects to
- Gmail
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Gmail account, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on an arriving email.
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. 11 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 11 steps before you point it at anything that matters.