Predict churn risk and trigger retention actions with OpenAI and Google Sheets
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 11 nodes and runs when an HTTP POST request hits its webhook URL (plus 1 other trigger). Along the way it connects AI Agent and OpenAI Chat Model. It also calls api.sendgrid.com and sheets.googleapis.com over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 1 other trigger).
- Prepare Event Context (Edit Fields (Set)): sets 8 fields: userId, eventType, sessionData…
- Python - Detect Drop-off Signals (Code): runs custom Python code
- Filter: keeps only the items that match a condition
- AI - Predict Drop-off Risk & Recommend Actions (AI Agent): runs an AI agent, with model: OpenAI Chat Model
- Wait: pauses before continuing
- JS - Format Recommendation (Code): runs custom JavaScript code
- Send Personalized Retention Message (HTTP Request): calls api.sendgrid.com (POST)
- Update Retention Tracker (HTTP Request): calls sheets.googleapis.com (POST)
Services it uses
HTTP calls to: api.sendgrid.com, sheets.googleapis.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI - Predict Drop-off Risk & Recommend Actions (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent..
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI - Predict Drop-off Risk & Recommend Actions (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Webhook
n8n-nodes-base.webhook - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - Filter
n8n-nodes-base.filter - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Wait
n8n-nodes-base.wait
From the author
This workflow automatically ingests real-time user behavior events, detects drop-off points across the customer journey, predicts churn risk using AI, and triggers targeted retention actions while logging everything for analysis. Who’s it for • Product teams…