Send advice from three AI personas via LINE, Gemini, and Google Sheets

by Ryo Sayama ✓ · 100 views · created 2026-03-25 · Support Chatbot, AI Chatbot

What this workflow does

This AI workflow has 12 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Gemini Chat Model and Google Sheets. It also calls api.line.me over HTTP.

How it runs

Trigger: When an HTTP POST request hits its webhook URL.

1. Set config (Edit Fields (Set)): sets 3 fields: LINE_CHANNEL_ACCESS_TOKEN, SHEET_ID, HISTORY_SHEET_NAME
2. Parse LINE event (Code): runs custom JavaScript code
3. Skip if no text event (If): checks a condition and branches into true / false
4. Respond OK (skip) (Respond to Webhook): sends the response back to the webhook caller
5. Build context (Code): runs custom JavaScript code
6. Generate advice with Gemini (Basic LLM Chain): sends a prompt to an LLM, with model: Google Gemini Chat Model
7. Parse Gemini response (Code): runs custom JavaScript code
8. Save advice to Sheets (Google Sheets): append
9. Send Flex Message to LINE (HTTP Request): calls api.line.me (POST)
10. Respond OK (Respond to Webhook): sends the response back to the webhook caller

Services it uses

Google Gemini Chat ModelGoogle Sheets

HTTP calls to: api.line.me

Before you upgrade to n8n 3.0

Nodes used (9)

• Webhookn8n-nodes-base.webhook
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• Google Sheetsn8n-nodes-base.googleSheets
• HTTP Requestn8n-nodes-base.httpRequest

From the author

Who is this for Anyone who wants a fun and practical AI chatbot on LINE. Great for people who enjoy getting advice from multiple angles — whether they face work stress, personal dilemmas, or everyday decisions. What this workflow does When a user sends a text…

View the original on n8n.io → Check your own copy