Every morning each tenant gets a renewal risk score from late payments, open maintenance issues, months left on the lease, and the tone of their recent messages, with high-risk tenants flagged to you in Slack and everyone else sent a renewal or check-in email
An n8n template by iamvaar runs once a day, loads your own scoring weights, and reads each tenant's row from a Google Sheets tenant list. Rule-based steps score payment friction, maintenance friction, and how close the lease end is from the sheet's columns. A Google Gemini model (gemini-3.1-flash-lite) reads the tenant's recent portal messages, review text, and emails and returns a 0 to 100 sentiment risk score with a one-sentence summary. The workflow combines these into a weighted churn risk score and a High, Medium, or Low label. High-risk tenants get a flag and score written back to the sheet and a Slack alert to the property manager; Medium and Low tenants get their score written back and a tailored renewal or check-in email through Gmail.
At a glance
- Tools used
- n8nGoogle GeminiGoogle SheetsSlackGmail
- Category
- Brokerage ops
- Audience
- property manager, landlord
- Difficulty
- Builder
- Source
- Score tenant churn risk with Google Sheets, Gemini, Gmail and Slack
iamvaar (n8n creator) · n8n template · Sep 11, 2026 - First step
- Fill the tenant sheet with ten current tenants, including two you know are unhappy and two you expect to renew, run the workflow once with the Gmail step turned off, and check whether the High, Medium, and Low labels match what you already know before any email goes out.
Compliance note: Use the score only to decide who gets a call or a renewal offer first, never to deny a renewal or change terms for one tenant, and keep message content out of any factor tied to a protected class under fair housing law.
Suggested prompt
Written by this directory, inspired by the source. Replace the [bracketed] parts.
You score how likely a tenant is to leave at lease end, based only on the tenant's own recent messages. Read the portal messages, review text, and emails below. Return JSON only: {"sentiment_score": integer 0 to 100 where 100 means the most negative tone and highest move-out risk, "sentiment_summary": one sentence naming the specific complaint or praise, such as a repeated repair request or a thank-you for a fast fix}. Do not guess at anything the messages do not say. Tenant ID: [tenant ID]. Portal messages: [paste]. Review text: [paste]. Emails: [paste]
Get 50 AI Prompts for Real Estate Agents, free
Subscribe to the Daily 5 and download the 48-page PDF right away. The prompts help with:
- Getting more leads from the contacts already in your CRM
- Faster follow-up, so no text or inquiry goes unanswered
- Less time on listing descriptions, paperwork, and showing instructions
- Copy-paste prompts tested by working agents, brokers, and landlords
- Five new real-world AI use cases every weekday morning in the Daily 5
Confirm by email. Unsubscribe in one click. Review every AI draft for accuracy and fair housing compliance before you send it.