Generate overdue lead follow-up Gmail drafts with Google Sheets and Gemini
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
Nodes used (11)
- Google Sheets
n8n-nodes-base.googleSheets - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Gmail
n8n-nodes-base.gmail - HTTP Request
n8n-nodes-base.httpRequest - Schedule Trigger
n8n-nodes-base.scheduleTrigger - If
n8n-nodes-base.if - Filter
n8n-nodes-base.filter - Slack
n8n-nodes-base.slack - Extract from File
n8n-nodes-base.extractFromFile - Code
n8n-nodes-base.code
What it does
Automatically identifies overdue sales leads and generates personalized follow-up emails using AI. How it works 1. Runs every weekday 2. Reads leads from Google Sheets 3. Filters leads with no contact for 5+ days 4. Downloads last meeting transcript from Google Drive 5. Uses Google Gemini to write a personalized email 6. Saves the email as a Gmail Draft for review 7. Updates lead status in the Sheet Setup - Google Sheets with columns: Current Status, Last Contact, Name, Company, Email, Meeting Transcript, Sales Rep - Google Drive access for transcript files - Google Gemini API key (free from Google AI Studio) - Gmail account - Slack workspace Supported file types - PDF - TXT Notes - Emails are saved as drafts only — not sent automatically - Supported lead statuses: New - Skips leads with status: Draft Created, Sent, Closed Inspiration This workflow was built to solve a real problem at an educational institute. The sales team needed someone to remind them about follow-ups and draft personalized emails — but hiring a personal assistant wasn't financially feasible. Based on that, this system acts as that assistant: it tracks overdue leads, reads meeting transcripts, and writes personalized follow-up emails automatically. I kept this stack free where possible — using Google Gemini's free tier for AI. For small sales teams, I believe the daily token limits are more than sufficient, making this a zero-cost automation.