Cold email icebreaker generator with Apify, GPT-4 & website scraping

3129 views

2/3/2026

Deep Multiline Icebreaker System (AI-Powered Cold Email Personalization)

Categories: Lead Generation, AI Marketing, Sales Automation

This workflow creates an advanced AI-powered cold email personalization system that achieves 5-10% reply rates by generating deeply personalized multi-line icebreakers. The system scrapes comprehensive website data, analyzes multiple pages per prospect, and uses advanced AI prompting to create custom email openers that make recipients believe you've personally researched their entire business.

Benefits

Superior Response Rates - Achieves 5-10% reply rates vs. 1-2% for standard cold email campaigns
Deep Website Intelligence - Scrapes and analyzes multiple pages per prospect, not just homepages
Advanced AI Personalization - Uses sophisticated prompting techniques with examples and formatting rules
Complete Lead Pipeline - From Apollo search to personalized icebreakers in Google Sheets
Scalable Processing - Handle hundreds of prospects with intelligent batching and error handling
Revenue-Focused Approach - System designed around proven $72K/month agency methodologies

How It Works

Apollo Lead Acquisition:

Integrates directly with Apollo.io search URLs through Apify scraper
Processes 500+ leads per search with comprehensive contact data
Filters for prospects with both email addresses and accessible websites

Multi-Page Website Scraping:

Scrapes homepage to extract all internal website links
Processes relative URLs and filters out external/irrelevant links
Performs intelligent batching to prevent IP blocking during scraping

Comprehensive Content Analysis:

Converts HTML to markdown for efficient AI processing
Uses GPT-4 to generate detailed abstracts of each webpage
Aggregates insights from multiple pages into comprehensive prospect profiles

Advanced AI Icebreaker Generation:

Employs sophisticated prompting with system messages, examples, and formatting rules
Uses proven icebreaker templates that reference non-obvious website details
Generates personalized openers that imply deep manual research

Smart Data Processing:

Removes duplicate URLs and handles scraping errors gracefully
Implements token limits to control AI processing costs
Organizes final output in structured Google Sheets format

Required Google Sheets Setup

Create a Google Sheet with these exact tab and column structures:

Search URLs Tab:

URL - Contains Apollo.io search URLs for your target audiences

Leads Tab (Output):

first_name - Contact's first name
last_name - Contact's last name
email - Contact's email address
website_url - Company website URL
headline - Job title/position
location - Geographic location
phone_number - Contact phone (if available)
multiline_icebreaker - AI-generated personalized opener

Setup Instructions:

Create Google Sheet with "Search URLs" and "Leads" tabs
Add your Apollo search URLs to the first tab (one per row)
Connect Google Sheets OAuth credentials in n8n
Update the Google Sheets document ID in all sheet nodes
The workflow reads from Search URLs and outputs to Leads automatically

Apollo Search URL Format: Your search URLs should look like: https://app.apollo.io/#/people?personLocations[]=United%20States&personTitles[]=ceo&qKeywords=marketing%20agency&page=1

Business Use Cases

AI Automation Agencies - Generate high-converting prospect outreach for service-based businesses
B2B Sales Teams - Create personalized cold email campaigns that actually get responses
Marketing Agencies - Offer premium personalization services to clients
Consultants - Build authority through deeply researched prospect outreach
SaaS Companies - Improve demo booking rates through personalized messaging
Professional Services - Stand out from generic sales emails with custom insights

Revenue Potential

This system transforms cold email economics:

5-10x Higher Response Rates than standard cold email approaches
$72K/month proven methodology - exact system used to scale successful AI agency
Premium Positioning - prospects assume you've done extensive manual research
Scalable Personalization - process hundreds of prospects daily vs. manual research

Difficulty Level: Advanced
Estimated Build Time: 3-4 hours
Monthly Operating Cost: ~$150 (Apollo + Apify + OpenAI + Email platform APIs)

Watch My Complete Live Build

Want to see me build this entire deep personalization system from scratch? I walk through every component live - including the AI prompting strategies, website scraping logic, error handling, and the exact techniques that generate 5-10% reply rates.

🎥 See My Live Build Process: "I Deep-Personalized 1000+ Cold Emails Using THIS AI System (FREE TEMPLATE)"

This comprehensive tutorial shows the real development process - including advanced AI prompting, multi-page scraping architecture, and the proven icebreaker templates that have generated over $72K/month in agency revenue.

Set Up Steps

Apollo & Apify Integration:

Configure Apify account with Apollo scraper access
Set up API credentials and test lead extraction
Define target audience parameters and lead qualification criteria

Google Sheets Database Setup:

Create multi-sheet structure (Search URLs, Leads)
Configure proper column mappings for lead data
Set up Google Sheets API credentials and permissions

Website Scraping Infrastructure:

Configure HTTP request nodes with proper redirect handling
Set up error handling for websites that can't be scraped
Implement intelligent batching with split-in-batches nodes

AI Content Processing:

Set up OpenAI API credentials with appropriate rate limits
Configure dual-AI approach (page summarization + icebreaker generation)
Implement token limiting to control processing costs

Advanced Icebreaker Generation:

Configure sophisticated AI prompting with system messages
Set up example-based learning with input/output pairs
Implement formatting rules for natural-sounding personalization

Quality Control & Testing:

Test complete workflow with small prospect batches
Validate AI output quality and personalization accuracy
Monitor response rates and optimize messaging templates

Advanced Optimizations

Scale the system with:

Industry-Specific Templates: Customize icebreaker formats for different verticals
A/B Testing Framework: Test different AI prompt variations and templates
CRM Integration: Automatically add qualified responders to sales pipelines
Response Tracking: Monitor which personalization elements drive highest engagement
Multi-Touch Sequences: Create follow-up campaigns based on initial response data

Important Considerations

AI Token Management: System includes intelligent token limiting to control OpenAI costs
Scraping Ethics: Built-in delays and error handling prevent website overload
Data Quality: Filtering logic ensures only high-quality prospects with accessible websites
Scalability: Batch processing prevents IP blocking during high-volume scraping

Why This System Works

The key to 5-10% reply rates lies in making prospects believe you've done extensive manual research:

Non-obvious details from deep website analysis
Natural language patterns that avoid template detection
Company name abbreviation (e.g., "Love AMS" vs "Love AMS Professional Services")
Multiple page insights aggregated into compelling narratives

Check Out My Channel

For more advanced automation systems and proven business-building strategies that generate real revenue, explore my YouTube channel where I share the exact methodologies used to build successful automation agencies.

n8n Cold Email Icebreaker Generator with Apify & GPT-4 (Website Scraping)

This n8n workflow automates the process of generating personalized cold email icebreakers by scraping website content, extracting key information, and then using GPT-4 to craft compelling icebreakers. It's designed to streamline lead generation and outreach efforts, making your cold emails more effective and less time-consuming to create.

What it does

This workflow performs the following steps:

Triggers Manually: The workflow starts when manually executed, allowing you to initiate the process on demand.
Reads Input from Google Sheets: It fetches a list of target company websites from a specified Google Sheet, providing the initial data for the scraping process.
Loops Over Items: Each website URL from the Google Sheet is processed individually in a loop.
Scrapes Website Content (HTTP Request): For each URL, an HTTP Request is made to retrieve the raw HTML content of the website.
Extracts Relevant HTML (HTML Node): The raw HTML content is then processed to extract specific elements (e.g., <p> tags) that are likely to contain useful information for icebreaker generation.
Cleans and Prepares Data (Code Node): A custom Code node cleans the extracted HTML, removing unnecessary whitespace, special characters, and potentially irrelevant content, preparing it for AI processing.
Filters Content: The cleaned content is filtered to ensure only substantial and relevant text passages are passed on.
Removes Duplicates: Duplicate content snippets are removed to avoid redundancy and improve the quality of the input for the AI.
Limits Content Size: The amount of content passed to the AI is limited to prevent excessive token usage and focus on the most valuable information.
Aggregates Content: The filtered and cleaned content snippets are aggregated into a single, cohesive text block.
Generates Icebreaker with OpenAI (GPT-4): The aggregated website content is sent to the OpenAI GPT-4 model, which then generates a personalized cold email icebreaker based on the provided information.
Formats Output (Markdown): The generated icebreaker is formatted using Markdown for readability.
Edits Fields (Set Node): The final output is structured, potentially combining the original website URL with the generated icebreaker.
Writes Output to Google Sheets: The generated icebreaker, along with the original website URL, is written back to a specified Google Sheet, making it easy to review and use in your outreach campaigns.

Prerequisites/Requirements

To use this workflow, you will need:

n8n Instance: A running n8n instance (cloud or self-hosted).
Google Sheets Account: To store and retrieve website URLs and generated icebreakers. You'll need credentials configured in n8n for Google Sheets.
OpenAI API Key: To access the GPT-4 model for icebreaker generation. You'll need to set up an OpenAI credential in n8n.
Apify Account (Implicit): While not explicitly shown as an Apify node, the workflow description and directory name suggest that Apify might be used for advanced web scraping capabilities. If this is the case, an Apify account and API key would be required, potentially integrated via the HTTP Request node or a dedicated Apify node if present in a larger context. (Note: Based strictly on the provided JSON, Apify is not explicitly a node, but the directory name strongly suggests its intended use for website scraping. The HTTP Request node handles the scraping in this specific JSON.)

Setup/Usage

Import the workflow: Download the JSON file and import it into your n8n instance.
Configure Credentials:
- Google Sheets: Set up a Google Sheets credential (OAuth2 or API Key) in n8n.
- OpenAI: Set up an OpenAI API Key credential in n8n.
Update Google Sheets Node (ID: 18):
- Specify the Spreadsheet ID and Sheet Name where your website URLs are located.
- Configure the Operation to "Read" and ensure it reads the column containing the URLs.
Update HTTP Request Node (ID: 19):
- Ensure the URL expression correctly references the website URL from the Google Sheets input (e.g., {{ $json.url_column_name }}).
Update OpenAI Node (ID: 1250):
- Select your configured OpenAI credential.
- Review and adjust the prompt to guide GPT-4 in generating the desired icebreaker style. Ensure it references the aggregated website content (e.g., {{ $json.aggregated_content }}).
Update Google Sheets Node (Output):
- Specify the Spreadsheet ID and Sheet Name where you want to write the generated icebreakers.
- Configure the Operation to "Append Row" or "Update Row" and map the generated icebreaker and original URL fields correctly.
Activate the workflow: Once configured, activate the workflow.
Execute the workflow: Click the "Execute workflow" button on the Manual Trigger node to start the process.

Related Templates

Automate interior design lead qualification with AI & human approval to Notion

Overview This automated workflow intelligently qualifies interior design leads, generates personalized client emails, and manages follow-up through a human-approval process. Built with n8n, Claude AI, Telegram approval, and Notion database integration. ⚠️ Hosting Options This template works with both n8n Cloud and self-hosted instances. Most nodes are native to n8n, making it cloud-compatible out of the box. What This Template Does Automated Lead Management Pipeline: Captures client intake form submissions from website or n8n forms AI-powered classification into HOT/WARM/COLD categories based on budget, project scope, and commitment indicators Generates personalized outreach emails tailored to each lead type Human approval workflow via Telegram for quality control Email revision capability for rejected drafts Automated client email delivery via Gmail Centralized lead tracking in Notion database Key Features ✅ Intelligent Lead Scoring: Analyzes 12+ data points including budget (AED), space count, project type, timeline, and style preferences ✅ Personalized Communication: AI-generated emails reference specific client details, demonstrating genuine understanding ✅ Quality Control: Human-in-the-loop approval via Telegram prevents errors before client contact ✅ Smart Routing: Different workflows for qualified leads (meeting invitations) vs. unqualified leads (respectful alternatives) ✅ Revision Loop: Rejected emails automatically route to revision agent for improvements ✅ Database Integration: All leads stored in Notion for pipeline tracking and analytics Use Cases Interior design firms managing high-volume lead intake Architecture practices with complex qualification criteria Home renovation companies prioritizing project value Any service business requiring budget-based lead scoring Sales teams needing approval workflows before client contact Prerequisites Required Accounts & API Keys: Anthropic Claude API - For AI classification and email generation Telegram Bot Token - For approval notifications Gmail Account - For sending client emails (or any SMTP provider) Notion Account - For lead database storage n8n Account - Cloud or self-hosted instance Technical Requirements: Basic understanding of n8n workflows Ability to create Telegram bots via BotFather Gmail app password or OAuth setup Notion database with appropriate properties Setup Instructions Step 1: Clone and Import Template Copy this template to your n8n instance (cloud or self-hosted) All nodes will appear as inactive - this is normal Step 2: Configure Form Trigger Open the Client Intake Form Trigger node Choose your trigger type: For n8n forms: Configure form fields matching the template structure For webhook: Copy webhook URL and integrate with your website form Required form fields: First Name, Second Name, Email, Contact Number Project Address, Project Type, Spaces Included Budget Range, Completion Date, Style Preferences Involvement Level, Previous Experience, Inspiration Links Step 3: Set Up Claude AI Credentials Obtain API key from https://console.anthropic.com In n8n: Create new credential → Anthropic → Paste API key Apply credential to these nodes: AI Lead Scoring Engine Personalized Client Outreach Email Generator Email Revision Agent Step 4: Configure Telegram Approval Bot Create bot via Telegram's @BotFather Copy bot token Get your Telegram Chat ID (use @userinfobot) In n8n: Create Telegram credential with bot token Configure Human-in-the-Loop Email Approval node: Add your Chat ID Customize approval message format if desired Step 5: Set Up Gmail Sending Enable 2-factor authentication on Gmail account Generate app password: Google Account → Security → App Passwords In n8n: Create Gmail credential using app password Configure Client Email Delivery node with sender details Step 6: Connect Notion Database Create Notion integration at https://www.notion.so/my-integrations Copy integration token Create database with these properties: Client Name (Title), Email (Email), Contact Number (Phone) Project Address (Text), Project Type (Multi-select) Spaces Included (Text), Budget (Select), Timeline (Date) Classification (Select: HOT/WARM/COLD), Confidence (Select) Estimated Value (Number), Status (Select) Share database with your integration In n8n: Add Notion credential → Paste token Configure Notion Lead Database Manager with database ID Step 7: Customize Classification Rules (Optional) Open AI Lead Scoring Engine node Review classification criteria in the prompt: HOT: 500k+ AED, full renovations, 2+ spaces WARM: 100k+ AED, 2+ spaces COLD: <100k AED OR single space Adjust thresholds to match your business requirements Modify currency if not using AED Step 8: Personalize Email Templates Open Personalized Client Outreach Email Generator node Customize: Company name and branding Signature placeholders ([Your Name], [Title], etc.) Tone and style preferences Alternative designer recommendations for COLD leads Step 9: Test the Workflow Activate the workflow Submit a test form with sample data Monitor each node execution in n8n Check Telegram for approval message Verify email delivery and Notion database entry Step 10: Set Up Error Handling (Recommended) Add error workflow trigger Configure notifications for failed executions Set up retry logic for API failures Workflow Node Breakdown Client Intake Form Trigger Captures lead data from website forms or n8n native forms with all project details. AI Lead Scoring Engine Analyzes intake data using structured logic: budget validation, space counting, and multi-factor evaluation. Returns HOT/WARM/COLD classification with confidence scores. Lead Classification Router Routes leads into three priority workflows based on AI classification, optimizing resource allocation. Sales Team Email Notifier Sends instant alerts to sales representatives with complete lead details and AI reasoning for internal tracking. Personalized Client Outreach Email Generator AI-powered composer creating tailored responses demonstrating genuine understanding of client vision, adapted by lead type. Latest Email Version Controller Captures most recent email output ensuring only final approved version proceeds to delivery. Human-in-the-Loop Email Approval Telegram-based review checkpoint sending generated emails to team member for quality control before client delivery. Approval Decision Router Evaluates reviewer's response, routing approved emails to client delivery or rejected emails to revision agent. Email Revision Agent AI-powered editor refining rejected emails based on feedback while maintaining personalization and brand voice. Client Email Delivery Sends final approved personalized emails demonstrating understanding of project vision with clear next steps. Notion Lead Database Manager Records all potential clients with complete intake data, classification results, and tracking information for pipeline management. Customization Tips Adjust Classification Thresholds: Modify budget ranges and space requirements in the AI Lead Scoring Engine prompt to match your market and service level. Multi-Language Support: Update all AI agent prompts with instructions for your target language. Claude supports 100+ languages. Additional Routing: Add branches for special cases like urgent projects, VIP clients, or specific geographic regions. CRM Integration: Replace Notion with HubSpot, Salesforce, or Airtable using respective n8n nodes. SMS Notifications: Add Twilio node for immediate HOT lead alerts to mobile devices. Troubleshooting Issue: Telegram approval not received Verify bot token is correct Confirm chat ID matches your Telegram account Check bot is not blocked Issue: Claude API errors Verify API key validity and credits Check prompt length isn't exceeding token limits Review rate limits on your Anthropic plan Issue: Gmail not sending Confirm app password (not regular password) is used Check "Less secure app access" if using older method Verify daily sending limits not exceeded Issue: Notion database not updating Confirm integration has access to database Verify property names match exactly (case-sensitive) Check property types align with data being sent Template Metrics Execution Time: ~30-45 seconds per lead (including AI processing) API Calls: 2-3 Claude requests per lead (classification + email generation, +1 if revision) Cost Estimate: ~$0.05-0.15 per lead processed (based on Claude API pricing) Support & Community n8n Community Forum: https://community.n8n.io Template Issues: Report bugs or suggest improvements via n8n template feedback Claude Documentation: https://docs.anthropic.com Notion API Docs: https://developers.notion.com License This template is provided as-is under MIT license. Modify and adapt freely for your business needs. --- Version: 1.0 Last Updated: October 2025 Compatibility: n8n v1.0+ (Cloud & Self-Hosted), Claude API v2024-10+

By Jameson Kanakulya

201

Automated UGC video generator with Gemini images and SORA 2

This workflow automates the creation of user-generated-content-style product videos by combining Gemini's image generation with OpenAI's SORA 2 video generation. It accepts webhook requests with product descriptions, generates images and videos, stores them in Google Drive, and logs all outputs to Google Sheets for easy tracking. Main Use Cases Automate product video creation for e-commerce catalogs and social media. Generate UGC-style content at scale without manual design work. Create engaging video content from simple text prompts for marketing campaigns. Build a centralized library of product videos with automated tracking and storage. How it works The workflow operates as a webhook-triggered process, organized into these stages: Webhook Trigger & Input Accepts POST requests to the /create-ugc-video endpoint. Required payload includes: product prompt, video prompt, Gemini API key, and OpenAI API key. Image Generation (Gemini) Sends the product prompt to Google's Gemini 2.5 Flash Image model. Generates a product image based on the description provided. Data Extraction Code node extracts the base64 image data from Gemini's response. Preserves all prompts and API keys for subsequent steps. Video Generation (SORA 2) Sends the video prompt to OpenAI's SORA 2 API. Initiates video generation with specifications: 720x1280 resolution, 8 seconds duration. Returns a video generation job ID for polling. Video Status Polling Continuously checks video generation status via OpenAI API. If status is "completed": proceeds to download. If status is still processing: waits 1 minute and retries (polling loop). Video Download & Storage Downloads the completed video file from OpenAI. Uploads the MP4 file to Google Drive (root folder). Generates a shareable Google Drive link. Logging to Google Sheets Records all generation details in a tracking spreadsheet: Product description Video URL (Google Drive link) Generation status Timestamp Summary Flow: Webhook Request → Generate Product Image (Gemini) → Extract Image Data → Generate Video (SORA 2) → Poll Status → If Complete: Download Video → Upload to Google Drive → Log to Google Sheets → Return Response If Not Complete: Wait 1 Minute → Poll Status Again Benefits: Fully automated video creation pipeline from text to finished product. Scalable solution for generating multiple product videos on demand. Combines cutting-edge AI models (Gemini + SORA 2) for high-quality output. Centralized storage in Google Drive with automatic logging in Google Sheets. Flexible webhook interface allows integration with any application or service. Retry mechanism ensures videos are captured even with longer processing times. --- Created by Daniel Shashko

By Daniel Shashko

1166

Track personal finances in Google Sheets with AI agent via Slack

Who's it for This workflow is perfect for individuals who want to maintain detailed financial records without the overhead of complex budgeting apps. If you prefer natural language over data entry forms and want an AI assistant to handle the bookkeeping, this template is for you. It's especially useful for: People who want to track cash and online transactions separately Anyone who lends money to friends/family and needs debt tracking Users comfortable with Slack as their primary interface Those who prefer conversational interactions over manual spreadsheet updates What it does This AI-powered finance tracker transforms your Slack workspace into a personal finance command center. Simply mention your bot with transactions in plain English (e.g., "₹500 cash food, borrowed ₹1000 from John"), and the AI agent will: Parse transactions using natural language understanding via Google Gemini Calculate balance changes for cash and online accounts Show a preview of changes before saving anything Update Google Sheets only after you approve Track debts (who owes you, who you owe, repayments) Send daily reminders at 11 PM with current balances and active debts The workflow maintains conversational context using PostgreSQL memory, so you can say things like "yesterday's transactions" or "that payment to Sarah" and it understands the context. How it works Scheduled Daily Check-in (11 PM) Fetches current balances from Google Sheets Retrieves all active debts Formats and sends a Slack message with balance summary Prompts you to share the day's transactions AI Agent Transaction Processing When you mention the bot in Slack: Phase 1: Parse & Analyze Extracts amount, payment type (cash/online), category (food, travel, etc.) Identifies transaction type (expense, income, borrowed, lent, repaid) Stores conversation context in PostgreSQL memory Phase 2: Calculate & Preview Reads current balances from Google Sheets Calculates new balances based on transactions Shows formatted preview with projected changes Waits for your approval ("yes"/"no") Phase 3: Update Database (only after approval) Logs transactions with unique IDs and timestamps Updates debt records with person names and status Recalculates and stores new balances Handles debt lifecycle (Active → Settled) Phase 4: Confirmation Sends success message with updated balances Shows active debts summary Includes logging timestamp Requirements Essential Services: n8n instance (self-hosted or cloud) Slack workspace with admin access Google account Google Gemini API key PostgreSQL database Recommended: Claude AI model (mentioned in workflow notes as better alternative to Gemini) How to set up Google Sheets Setup Create a new Google Sheet with three tabs named exactly: Balances Tab: | Date | CashBalance | OnlineBalance | Total_Balance | |------|--------------|----------------|---------------| Transactions Tab: | TransactionID | Date | Time | Amount | PaymentType | Category | TransactionType | PersonName | Description | Added_At | |----------------|------|------|--------|--------------|----------|------------------|-------------|-------------|----------| Debts Tab: | PersonName | Amount | Type | Datecreated | Status | Notes | |-------------|--------|------|--------------|--------|-------| Add header rows and one initial balance row in the Balances tab with today's date and starting amounts. Slack App Setup Go to api.slack.com/apps and create a new app Under OAuth & Permissions, add these Bot Token Scopes: app_mentions:read chat:write channels:read Install the app to your workspace Copy the Bot User OAuth Token Create a dedicated channel (e.g., personal-finance-tracker) Invite your bot to the channel Google Gemini API Visit ai.google.dev Create an API key Save it for n8n credentials setup PostgreSQL Database Set up a PostgreSQL database (you can use Supabase free tier): Create a new project Note down connection details (host, port, database name, user, password) The workflow will auto-create the required table n8n Workflow Configuration Import the workflow and configure: A. Credentials Google Sheets OAuth2: Connect your Google account Slack API: Add your Bot User OAuth Token Google Gemini API: Add your API key PostgreSQL: Add database connection details B. Update Node Parameters All Google Sheets nodes: Select your finance spreadsheet Slack nodes: Select your finance channel Schedule Trigger: Adjust time if you prefer a different check-in hour (default: 11 PM) Postgres Chat Memory: Change sessionKey to something unique (e.g., financetrackeryour_name) Keep tableName as n8nchathistory_finance or rename consistently C. Slack Trigger Setup Activate the "Bot Mention trigger" node Copy the webhook URL from n8n In Slack App settings, go to Event Subscriptions Enable events and paste the webhook URL Subscribe to bot event: app_mention Save changes Test the Workflow Activate both workflow branches (scheduled and agent) In your Slack channel, mention the bot: @YourBot ₹100 cash snacks Bot should respond with a preview Reply "yes" to approve Verify Google Sheets are updated How to customize Change Transaction Categories Edit the AI Agent's system message to add/remove categories. Current categories: travel, food, entertainment, utilities, shopping, health, education, other Modify Daily Check-in Time Change the Schedule Trigger's triggerAtHour value (0-23 in 24-hour format). Add Currency Support Replace ₹ with your currency symbol in: Format Daily Message code node AI Agent system prompt examples Switch AI Models The workflow uses Google Gemini, but notes recommend Claude. To switch: Replace "Google Gemini Chat Model" node Add Claude credentials Connect to AI Agent node Customize Debt Types Modify AI Agent's system prompt to change debt handling logic: Currently: IOwe and TheyOwe_Me You can add more types or change naming Add More Payment Methods Current: cash, online To add more (e.g., credit card): Update AI Agent prompt Modify Balances sheet structure Update balance calculation logic Change Approval Keywords Edit AI Agent's Phase 2 approval logic to recognize different approval phrases. Add Spending Analytics Extend the daily check-in to calculate: Weekly/monthly spending summaries Category-wise breakdowns Use additional Code nodes to process transaction history Important Notes ⚠️ Never trigger with normal messages - Only use app mentions (@botname) to avoid infinite loops where the bot replies to its own messages. 💡 Context Awareness - The bot remembers conversation history, so you can reference "yesterday", "last week", or previous transactions naturally. 🔒 Data Privacy - All your financial data stays in your Google Sheets and PostgreSQL database. The AI only processes transaction text temporarily. 📊 Backup Regularly - Export your Google Sheets periodically as backup. --- Pro Tips: Start with small test transactions to ensure everything works Use consistent person names for debt tracking The bot understands various formats: "₹500 cash food" = "paid 500 rupees in cash for food" You can batch transactions in one message: "₹100 travel, ₹200 food, ₹50 snacks"

By Habeeb Mohammed

448