This workflow follows the Chainllm → Gmail recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "13f8de57-7247-4be1-8fc4-dddc1a7d677e",
"name": "Scheduled Start: Daily Churn Check",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
160,
0
],
"parameters": {
"rule": {
"interval": [
{}
]
}
},
"typeVersion": 1.2
},
{
"id": "8f52666a-7247-4058-a775-2be80e3b4c0e",
"name": "Fetch Customer Data from Sheet",
"type": "n8n-nodes-base.googleSheets",
"position": [
440,
0
],
"parameters": {
"options": {
"returnFirstMatch": false
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1698897552,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit#gid=1698897552",
"cachedResultName": "Customer Data"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit?usp=drivesdk",
"cachedResultName": "Medium Post Automation"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "37951981-3c3d-4434-8782-51e9129f0bbc",
"name": "Filter High Churn Risk & No Campaign Customers",
"type": "n8n-nodes-base.filter",
"position": [
760,
0
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "9b78accc-0926-4537-8ce9-70206dd45525",
"operator": {
"type": "number",
"operation": "gt"
},
"leftValue": "={{ $json.predicted_churn_score.toNumber() }}",
"rightValue": 0.7
}
]
}
},
"typeVersion": 2.2,
"alwaysOutputData": true
},
{
"id": "4152752b-3ba3-4af0-aec8-aba9fc0424d9",
"name": "Check if Eligible Customers Found",
"type": "n8n-nodes-base.if",
"position": [
1140,
0
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2b03f228-f10c-43c1-90f8-a2ef397d2e0b",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
},
"leftValue": "={{ $json.isEmpty() }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "c1164b8f-4497-4763-bb42-7187e9f2f4d2",
"name": "Process Each Eligible Customer",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1640,
-320
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "8896a776-ed5b-431a-908b-663fa8475c77",
"name": "Generate Win-Back Offer",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
2100,
-300
],
"parameters": {
"text": "=",
"messages": {
"messageValues": [
{
"message": "=\n**You are an AI assistant designed to analyze customer data and determine a win-back offer based on specific churn prediction scores and preferences.**\n\n**Input:** You will receive customer data as a JSON object.\n\n**Task:** Analyze the fields `'predicted_churn_score': {{ $json.predicted_churn_score }}` and `'preferred_categories': \"{{ $json.preferred_categories }}\"` in the input JSON. Apply the following rules to determine the appropriate offer details:\n\n**Rules:**\n\n1. If `predicted_churn_score` is greater than or equal to 0.7 and less than or equal to 0.8:\n\n * Offer Type: `INFORMATIONAL`\n * Offer Value: `0`\n * Offer Title: `Special Advantage on Books Just for You`\n * Offer Details: Create a message encouraging the customer to explore new products in their preferred categories. To make it more specific, select *one* of the preferred categories and include a *typical product type* from that category.\n Example: `\"Exciting new [product type, e.g., novels] just arrived in your favorite [Preferred Category Name] category! Check out what's new in your other favorite categories too: [List of Other Preferred Categories]!\"`\n\n2. If `predicted_churn_score` is greater than 0.8 and less than or equal to 0.9:\n\n * Offer Type: `BONUS_POINTS`\n * Offer Value: `200`\n * Offer Title: `Special Advantage on Books Just for You`\n * Offer Details: Create a message offering 200 bonus points for purchases made specifically in the \"Books\" category.\n Example: `\"Earn 200 bonus points on your next purchase in the Books category!\"`\n\n3. If `predicted_churn_score` is greater than 0.9 and less than or equal to 1.0:\n\n * Offer Type: `DISCOUNT_PERCENTAGE`\n * Offer Value: `20`\n * Offer Title: `Special Advantage on Books Just for You`\n * Offer Details: Create a message offering a 20% discount on a future purchase specifically in the \"Books\" category.\n Example: `\"Enjoy a 20% discount on your next purchase in the Books category!\"`\n\n**Output:** Generate a JSON object that includes the determined offer details. The OUTPUT MUST STRICTLY FOLLOW THE STRUCTURE BELOW and INCLUDE ONLY THE JSON OBJECT. Do not add any other text or explanation.\n\n**Output Structure:**\n\n{\n \"customer_id\": string, // Customer ID from the input data\n \"action_taken\": \"SENT_WINBACK_OFFER\", // Action taken: win-back offer sent (constant in this example)\n \"offer_type\": string, // Offer type: INFORMATIONAL, BONUS_POINTS, or DISCOUNT_PERCENTAGE\n \"offer_value\": number, // Offer value: 0 (informational), 200 (points), or 20 (discount)\n \"offer_title\": string, // Message title\n \"offer_details\": string, // Message in Turkish, created based on rules and preferred categories\n \"communication_channel\": \"email\", // Communication channel (constant in this example)\n \"timestamp\": string // Current timestamp in ISO 8601 format (e.g., \"YYYY-MM-DDTHH:mm:ssZ\"). Note: In an actual n8n workflow, you may prefer to add the real timestamp using a separate node or expression after the LLM node.\n}\n\n"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "b89954e9-7689-47e6-bf15-3089f3863ca9",
"name": "(LLM Model for Offer Generation)",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2060,
-120
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-pro-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ee485123-32be-447b-80f3-303e3a046207",
"name": "(Parse Offer JSON)",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
2260,
-100
],
"parameters": {
"jsonSchemaExample": "{\n \"customer_id\": \"CUST_001\",\n \"action_taken\": \"SENT_WINBACK_OFFER\",\n \"offer_type\": \"BONUS_POINTS\",\n \"offer_value\": 200,\n \"offer_title\": \"Huge Offer!\",\n \"offer_details\": \"Get 200 bonus points when you shop in the Kitap category!\",\n \"communication_channel\": \"email\",\n \"timestamp\": \"2024-06-08T09:05:00Z\"\n}"
},
"typeVersion": 1.2
},
{
"id": "005890c2-f77d-4d0d-add2-496642464a9f",
"name": "Log Sent Offer in System Log",
"type": "n8n-nodes-base.googleSheets",
"position": [
2640,
-220
],
"parameters": {
"columns": {
"value": {
"date": "={{ $json.output.timestamp }}",
"system_log": "={{ $json.output.action_taken }}",
"customer_id": "={{ $json.output.customer_id }}"
},
"schema": [
{
"id": "system_log",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "system_log",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "date",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "date",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "customer_id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "customer_id",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"system_log"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 157558698,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit#gid=157558698",
"cachedResultName": "SYSTEM_LOG"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit?usp=drivesdk",
"cachedResultName": "OnurPolat05 N8N Db"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "98295978-21f1-420f-8e9c-4014d53ffb16",
"name": "Send Win-Back Offer via Email",
"type": "n8n-nodes-base.gmail",
"position": [
2880,
-120
],
"parameters": {
"sendTo": "={{ $('Process Each Eligible Customer').item.json.user_mail }}",
"message": "={{ $json.output.offer_details }}",
"options": {},
"subject": "={{ $json.output.offer_title }}",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "13095156-a54f-432f-8d10-209ddc30680a",
"name": "Set 'Not Found' Status",
"type": "n8n-nodes-base.set",
"position": [
1620,
300
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e42f6e99-487d-4942-a133-879d62b28fe5",
"name": "system_log",
"type": "string",
"value": "NOT_FOUND"
},
{
"id": "4fe0abc3-e685-4ece-bee2-1ae4f6d3ca92",
"name": "date",
"type": "string",
"value": "={{ $now }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "1f823726-6483-40c1-b184-eac87886ded5",
"name": "Log 'Not Found' in System Log",
"type": "n8n-nodes-base.googleSheets",
"position": [
1940,
300
],
"parameters": {
"columns": {
"value": {
"date": "={{ $json.date }}",
"system_log": "={{ $json.system_log }}"
},
"schema": [
{
"id": "system_log",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "system_log",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "date",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "date",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"system_log"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 157558698,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit#gid=157558698",
"cachedResultName": "SYSTEM_LOG"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1hG2NMi-4fMa7D5qGonCN8bsYVya4L2TOB_8mI4XK-9k/edit?usp=drivesdk",
"cachedResultName": "OnurPolat05 N8N Db"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "c6828c9c-c39f-40b5-9197-1435915d3682",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
160,
-340
],
"parameters": {
"width": 380,
"height": 300,
"content": "# 00. Daily Start & Fetch Customer Data\n\n**Purpose:** Automatically triggers the workflow **once daily** based on the schedule set in the first node. It then fetches all customer data from the specified Google Sheet ('Customer Data' sheet) to identify potential churn risks for the day."
},
"typeVersion": 1
},
{
"id": "71d3f596-1413-4e97-81eb-ec701f15938d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1560,
540
],
"parameters": {
"color": 3,
"width": 540,
"height": 300,
"content": "# 03. Handle No Eligible Customers\n\n**Purpose:** This path executes if the initial filter finds *no* customers meeting the win-back criteria during the daily check.\n1. **Set Status:** Sets a variable indicating no eligible customers were found (`system_log = NOT_FOUND`).\n2. **Log Status:** Records this 'NOT_FOUND' status along with the current timestamp in the 'SYSTEM_LOG' Google Sheet. This helps track when the daily workflow ran but had no one to process."
},
"typeVersion": 1
},
{
"id": "0f076e97-7cf0-48b6-8808-db0f1863409e",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
-360
],
"parameters": {
"color": 2,
"width": 460,
"height": 280,
"content": "# 01. Filter & Branch\n\n**Purpose:** Filters the fetched customer data to identify those meeting specific win-back criteria:\n1. `predicted_churn_score` is greater than 0.7.\n2. No previous campaign date exists (`created_campaign_date` is empty - *Note: Verify this field's purpose or adjust logic if needed*).\nThen, it checks if any customers passed the filter. The workflow branches based on whether eligible customers were found."
},
"typeVersion": 1
},
{
"id": "d3493f09-7eba-4625-98db-83cf649dbbcf",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1700,
-760
],
"parameters": {
"color": 4,
"width": 600,
"height": 360,
"content": "# 02. Generate & Send Win-Back Offer (Loop)\n\n**Purpose:** Processes each eligible customer found in the previous step individually within a loop.\n1. **Generate Offer (Gemini):** Uses Google Gemini to create a personalized win-back offer (Informational, Bonus Points, or Discount) based on the customer's `predicted_churn_score` and `preferred_categories`. Outputs offer details in JSON format.\n2. **Log Sent Offer:** Records the successful generation and intent to send the offer (action_taken, timestamp, customer_id) in the 'SYSTEM_LOG' Google Sheet.\n3. **Send Email (Gmail):** Sends the generated offer details (`offer_title` and `offer_details`) via email to the customer's `user_mail`.\nThe loop continues until all eligible customers are processed."
},
"typeVersion": 1
},
{
"id": "2fc53a15-2bdd-48f5-9a74-44a2e028e7e0",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
-120
],
"parameters": {
"width": 400,
"height": 380,
"content": "# Example Customer Data\n\n\n{\n \"customer_id\": \"CUST_001\",\n \"last_purchase_date\": \"2024-01-10T10:00:00Z\",\n \"purchase_frequency_days\": 90,\n \"user_mail\":\"example@mail.com\",\n \"days_since_last_purchase\": 110,\n \"total_spent_usd\": 55.0,\n \"preferred_categories\": [\"Kitap\", \"Ofis Malzemeleri\"],\n \"predicted_churn_score\": 0.85,\n \"profile_tags\": [\"inactive_long_time\", \"low_spender\"],\n \"timestamp\": \"2024-06-08T09:00:00Z\"\n}\n"
},
"typeVersion": 1
}
],
"connections": {
"(Parse Offer JSON)": {
"ai_outputParser": [
[
{
"node": "Generate Win-Back Offer",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Set 'Not Found' Status": {
"main": [
[
{
"node": "Log 'Not Found' in System Log",
"type": "main",
"index": 0
}
]
]
},
"Generate Win-Back Offer": {
"main": [
[
{
"node": "Log Sent Offer in System Log",
"type": "main",
"index": 0
}
]
]
},
"Log Sent Offer in System Log": {
"main": [
[
{
"node": "Send Win-Back Offer via Email",
"type": "main",
"index": 0
}
]
]
},
"Send Win-Back Offer via Email": {
"main": [
[
{
"node": "Process Each Eligible Customer",
"type": "main",
"index": 0
}
]
]
},
"Fetch Customer Data from Sheet": {
"main": [
[
{
"node": "Filter High Churn Risk & No Campaign Customers",
"type": "main",
"index": 0
}
]
]
},
"Process Each Eligible Customer": {
"main": [
[],
[
{
"node": "Generate Win-Back Offer",
"type": "main",
"index": 0
}
]
]
},
"(LLM Model for Offer Generation)": {
"ai_languageModel": [
[
{
"node": "Generate Win-Back Offer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Check if Eligible Customers Found": {
"main": [
[
{
"node": "Process Each Eligible Customer",
"type": "main",
"index": 0
}
],
[
{
"node": "Set 'Not Found' Status",
"type": "main",
"index": 0
}
]
]
},
"Scheduled Start: Daily Churn Check": {
"main": [
[
{
"node": "Fetch Customer Data from Sheet",
"type": "main",
"index": 0
}
]
]
},
"Filter High Churn Risk & No Campaign Customers": {
"main": [
[
{
"node": "Check if Eligible Customers Found",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
gmailOAuth2googlePalmApigoogleSheetsOAuth2Api
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow automates the identification of high-churn-risk customers and delivers personalised win-back offers via email, helping businesses retain valuable subscribers without manual effort. It targets marketing teams or customer success managers handling subscription services, where proactive retention can boost revenue. The key step involves fetching customer data from Google Sheets, filtering for at-risk individuals without recent campaigns, and using Google's Gemini AI to generate tailored offers before sending them through Gmail.
Use this workflow for daily or weekly churn checks in subscription-based models like SaaS or e-commerce, especially when integrating with existing Google Sheets for customer tracking. Avoid it for one-off analyses or non-email outreach, as it relies on scheduled automation and batch processing. Common variations include adjusting the cron trigger for different frequencies or swapping Gmail for another email service like SendGrid to suit varied campaign needs.
About this workflow
Filter Schedule. Uses scheduleTrigger, googleSheets, splitInBatches, chainLlm. Scheduled trigger; 17 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Doc Processing. Uses chainLlm, lmChatGroq, googleDrive, googleSheets. Scheduled trigger; 39 nodes.
Chain Llm, Groq Chat, Google Drive +3
WordPress Contact Form (CF7) Responses and Classification. Uses lmChatGoogleGemini, textClassifier, gmail, chainLlm. Webhook trigger; 24 nodes.
Google Gemini Chat, Text Classifier, Gmail +3
This workflow optimizes the management of inquiries received through a contact form (Contact Form 7 - CF7 Plugin) on a WordPress site, automating the process of classification, response drafting, and
Google Gemini Chat, Text Classifier, Gmail +3
Restaurant owners, retail store managers, and small business owners who want to stay on top of customer feedback without manually checking Google reviews multiple times a day. Perfect for businesses t
HTTP Request, Chain Llm, Google Sheets +3
This template automates the complete hiring pipeline for digital agencies managing applications across multiple job roles. When a candidate submits a Google Form with their CV, the system scores it wi
OpenRouter Chat, Output Parser Structured, Google Sheets +6