The flow
Starts it 1Model 9Logic 2Service 2
The steps in the order they run, from what starts it.
- 1Google Gemini Chat ModelLm Chat Google GeminiModel
- 2Google Gemini Chat Model1Lm Chat Google GeminiModel
- 3Google Gemini Chat Model2Lm Chat Google GeminiModel
- 4Structured Output ParserOutput Parser StructuredModel
- 5Structured Output Parser1Output Parser StructuredModel
- 6Structured Output Parser2Output Parser StructuredModel
- 7User Request - Telegram TriggerTelegram triggerStarts it
- 8Basic LLM ChainChain LlmModel
- 9Basic LLM Chain1Chain LlmModel
- 10AI AgentAgentModel
- 11Gets Requested Email(s)GmailService
- 12Sends (requested emails) via Telegram backTelegramService
- 13Set Parameters From User Request (for fetching emails)SetLogic
- 14Sets Parameters For ResponseSetLogic
How it's built
- Starts on
- An incoming Telegram message
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Gmail, Telegram
- Model
- Gemini
Questions
What does it need to run?
An n8n account, plus your own Gmail and Telegram accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.
What starts it?
It starts on an incoming Telegram message.
Does it use AI?
Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 14 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 14 steps before you point it at anything that matters.