Workflow Templates

AI Customer-Support Assistant that auto-maps any business site, answers WhatsApp in real time, and lets you earn or save thousands by replacing pricey SaaS chat tools. ⚡ What the workflow does Live “AI employee”* - the bot crawls pages on demand (products, policies, FAQs) so you *never** upload documents or fine-tune a model. No-code setup** - Drop in API keys, paste your domain, publish the webhook—ready in \~15 min. Chat memory** - each conversation turn is written to Supabase/Postgres and automatically replayed into the next prompt, letting the assistant remember context so follow-up questions feel natural and coherent even across long sessions. WhatsApp ready** - Free-form replies inside the 24-hour service window, automatically switches to a template when required (recommended by Meta). 🚀 Why you’ll love it | Benefit | Impact | | ------------------------- | --------------------------------------------------------------------- | | Zero content training | Point the AI Agent at any domain → go live. | | Save or earn money | Replace pricey SaaS chat tools or sell white-label bots to clients. | | Channel-agnostic | Ships with WhatsApp; swap one node for Telegram, Slack, or web chat. | | Flexible voice | Adjust tone & language by editing one prompt line. | 🧰 Prerequisites (all free-tier friendly) OpenAI key Meta WhatsApp Cloud API number + permanent token (easy setup) Supabase (or Postgres) URL for chat memory (easy setup) 🛠 5-step setup Import the template into n8n. Add credentials for OpenAI, WhatsApp, and Supabase. Enter your root domain in the root\_url variable. Point Meta’s Webhook to the n8n URL. Hit Execute Trigger and send “Hi” from WhatsApp—watch the bot answer with live data. 🔄 Easy to extend Voice & language** – change wording in the System Prompt. Escalation** – add an “If fallback” branch → Zendesk, email, live agents. Extra channels** – duplicate the reply node for Telegram or Slack. Commerce API hooks** – plug in Shopify, Woo, Stripe for order status or payments. 💡 Monetization ideas Replace costly SaaS seats.* Deploy the bot on your own server and *stop paying \$300–\$500 every month for third-party “AI support” platforms. Sell it as a service.* Spin up a branded instance for local shops, clinics, or e-commerce stores and *charge each client \$300–\$500 per month**—setup time is under 15 minutes. Upsell premium coverage (24/7 human hand-off) once the bot handles routine questions. Embed product links in answers and earn affiliate or upsell revenue automatically. Spin it up, connect a domain and a phone number, and you—or your customers—get enterprise-grade support without code, training, or ongoing licence fees.

🎯 Project Purpose This project automates the process of collecting and managing new leads submitted through a web form. It eliminates the need for manual data entry and ensures that each lead is: Properly recorded and time-stamped in a structured format Automatically communicated to the sales or support team Ready for follow-up, with a reminder system in place It’s a lightweight but effective solution suitable for freelancers, small teams, and growing businesses that want to streamline their lead intake process. 🛠️ Tools & Technologies Used Google Forms / Web Form** – Frontend for capturing leads Google Sheets** – Central database for storing lead information n8n** – Automation platform that connects and coordinates all services Gmail** – Handles email notifications for new leads Slack* *(optional) – Provides instant team notifications Date & Time nodes** – Tracks and manages lead response timing Conditional (IF) nodes** – Filters out duplicate and incomplete entries 🔄 Workflow Overview ✨ Key Features ✅ No-code integration using n8n ✅ Instant alerts via Gmail and/or Slack ✅ Google Sheets as an easily accessible backend ✅ Modular design — easy to expand with CRM tools (like HubSpot) ✅ Clean JSON structure and logic, beginner-friendly 📈 Possible Improvements Add email validation via external API (e.g., NeverBounce, Hunter) Integrate with a CRM for deeper automation Add lead scoring based on answers Include automatic follow-up emails after X days Schedule weekly summary reports via email 🧑🏻‍💻 Creator Information Developed by: Adem Tasin Adem T. 🌐 Website: Dataplusminus+- 📧 Email:dataplusminuss@gmail.com 💼 LinkedIn: Adem Tasin

Stop manually checking keyword rankings and let automation do the work for you. This comprehensive SEO monitoring workflow automatically tracks your keyword positions, compares them against your target URLs, and instantly alerts your team via Slack whenever rankings change - ensuring you never miss critical SEO movements. ✨ What This Workflow Does: 📊 Automated Rank Checking**: Continuously monitors keywords stored in Airtable 🔍 Real-Time SERP Analysis**: Uses Firecrawl API to fetch current search rankings 📈 Intelligent Comparison**: Compares current vs. previous rankings automatically 📝 Database Updates**: Updates Airtable records with new ranking data 🚨 Instant Alerts**: Sends Slack notifications only when rankings change 🎯 Target URL Matching**: Specifically tracks your domain's position in search results 🔧 Key Features: Trigger-based automation** that activates when Airtable data changes Smart rank comparison** logic that prevents false alerts Conditional notifications** - only alerts on actual ranking changes Clean data management** with automatic Airtable updates Team collaboration** through Slack integration Scalable monitoring** for unlimited keywords 📋 Prerequisites: Airtable account with Personal Access Token Firecrawl API key for SERP data Slack workspace with API access Basic Airtable setup with keyword data 🎯 Perfect For: SEO agencies managing multiple client campaigns Digital marketing teams tracking organic performance Content creators monitoring content rankings E-commerce businesses tracking product visibility Startups needing cost-effective SEO monitoring Any business serious about search visibility 💡 How It Works: Data Collection: Fetches keywords, target URLs, and current ranks from Airtable SERP Analysis: Queries Firecrawl API for real-time search results Rank Detection: Searches results for your target URL and determines position Smart Comparison: Compares new ranking against stored data Database Update: Updates Airtable with latest ranking information Conditional Alert: Sends Slack notification only if ranking changed Team Notification: Delivers actionable ranking updates to your team 📦 What You Get: Complete n8n workflow with all integrations configured Airtable template with proper field structure Firecrawl API integration setup Slack notification templates Comprehensive setup documentation Sample keyword data for testing 🚀 Benefits: Save Hours Weekly**: Eliminate manual rank checking Never Miss Changes**: Get instant alerts on ranking movements Team Alignment**: Keep everyone informed via Slack Historical Tracking**: Maintain ranking history in Airtable Cost Effective**: Replace expensive SEO tools with automation Scalable Solution**: Monitor unlimited keywords effortlessly 💡 Need Help or Want to Learn More? Created by Yaron Been 📧 Support: Yaron@nofluff.online 🎥 YouTube Tutorials: https://www.youtube.com/@YaronBeen/videos 💼 LinkedIn: https://www.linkedin.com/in/yaronbeen/ Discover more SEO automation workflows and digital marketing tutorials on my channels! 🏷️ Tags: SEO, Keyword Tracking, Airtable, Slack, Firecrawl, SERP, Automation, Rank Monitoring, Digital Marketing, Search Rankings

This n8n workflow template is designed to route user input to specialized agents (like a Reminder Agent, Email Agent, etc.) using a structured output from a language model. Here's a complete description of what it does and how each part works: 🔁 Workflow Purpose: This template receives a user's request via Webhook, processes it using an LLM, extracts structured data like the agent name and user query, and routes the input to the appropriate sub-workflow (agent) based on the specified agent type. 🧩 Workflow Breakdown: 1. Webhook (Trigger) Node: Webhook Purpose: Accepts a POST request from any frontend or API source. It contains the raw user input. 2. GPT Model (LLM Inference) Node: GPT 4o Mini Purpose: Interprets the user input and determines: Which agent should handle it (e.g., "Reminder Agent", "Email Agent", etc.) The actual user request (in structured format) 3. Auto-Fixing Output Parser Node: Auto-fixing Output Parser Purpose: Ensures that the output from the LLM matches the expected structure. If there's a mismatch, it automatically corrects it using a re-prompt. 4. Structured Output Parser Node: Structured Output Parser Purpose: Converts the language model's response into a strict JSON structure with keys like: "Agent Name" "user input" "sessionID" 5. Agent Router Node: Switch ("Agent Route") Purpose: Based on "Agent Name", it routes the input to one of the following sub-workflows: 📅 Reminder Agent 📧 Email Agent 🧾 Document Agent 🤝 Meeting Agent 6. Sub-Workflow Call (Execute Workflow) Each agent is implemented as a separate n8n workflow: The input is forwarded to the selected agent. For example, if "Agent Name" is "Reminder Agent", the workflow "Reminder Agent" is called with "user input". 7. Webhook Response After the sub-agent workflow finishes, a Respond to Webhook node sends the output back as an HTTP response. ✅ Key Features: Fully modular and extensible LLM-driven routing using OpenRouter GPT-4o Auto-corrects structured output errors Clean separation of concerns (agent logic is decoupled in sub-workflows) Easily add more agents by updating the switch logic 📦 Use Case Examples: User says: “Remind me to call my mom tomorrow.” → Routed to Reminder Agent User says: “Send an email to the HR team.” → Routed to Email Agent User says: “Schedule a meeting with John next week.” → Routed to Meeting Agent

AI Agent System Prompt 'Auto-Tuner' This workflow configures an AI agent which provides an edited system prompt for an autonomous AI agent Based on the following pieces of information provided by the user in an input form: Agent name Agent purpose What's working What's not working Current system prompt There are two additional form elements that I've marked as non-required but if you want to force more detail from the user you can mark these as required: Example prompt Example output This information gets sent to the AI agent which is configured with a system prompt of its own and the form elements are concatenated into a user prompt prompting the agent to evaluate the system prompt, deliver an improved version, and provide some notes for logging. The output structure is constrained with JSON. OpenAI 4o is recommended for its overall strong adherence to structured outputs. Once the agent delivers its improved system prompt, this gets passed to the user via email notification. The final delivery stage can be alternated according to user preference When This Is Useful Anyone working on AI agent configurations will likely be familiar with the pivotal importance of the system prompt in directing the desired behavior of the agent. Frequently this requires long hours of iteration before a consistent desired behaviour is achieved. Sometimes we can figure out what's working and not based on our own intuition and experience, but at other times soliciting the outside perspective of another AI tool can be a helpful way to consider alternative explanations or improve our own prompt engineering. This configuration is intended to speed up this iterative process and reduce the amount of time we spend working on system prompts to configure effective agent workflows

📬 Gmail to Google Drive Email Export Workflow (n8n) 🧩 Overview This n8n workflow automates the process of: Retrieving all emails from a specific sender using Gmail. Extracting essential fields like subject, message, and date. Formatting the email date to the desired time zone (e.g., IST). Exporting the parsed data as a CSV file. Uploading the file to a specified folder in Google Drive. 🛠 Nodes Breakdown 1. Start Workflow (Manual Trigger) Type**: Manual Trigger Purpose**: Initiates the workflow manually. 2. Gmail Node (Get All Emails) Type**: Gmail Operation**: getAll Filters**: sender: akhilgadiraju@gmail.com Returns**: All emails from the specified sender. Credentials**: Gmail OAuth2 - Akhil 3. Parse Data (Set Node) Purpose**: Extracts key fields from the email JSON. Mapped Fields**: id: Email ID subject: Email subject message: Email text time: Email date 4. Convert Time Field (Code Node) Purpose**: Converts the email time (ISO 8601) to a human-readable format. Output Format**: Local time using Asia/Kolkata timezone. Format: "Month Day, Year, Hour:Minute AM/PM" Customizable**: Change the timezone as needed: timeZone: 'Asia/Kolkata' 5. Convert to File Type**: Convert to File Node Purpose**: Converts JSON data to a downloadable .csv file. Output File**: CSV containing id, subject, message, and time. 6. Google Drive Type**: Google Drive Purpose**: Uploads the generated CSV file to Google Drive. Drive**: My Drive Folder**: Root File Name**: Current timestamp + _n8n_export.csv 7. End Workflow (NoOp) Purpose**: Final node to explicitly end the workflow. ✅ Use Cases Personal Email Archiving**: Back up or export emails from a specific sender (e.g., invoices, reports). Audit Logs**: Save conversations for compliance. Team Reports**: Aggregate project emails into a central file store. 🔧 Customization Guide | Customization | How to Do It | |---------------------------|------------------------------------------------------------| | Change Sender Email | Update the sender field in the Gmail node. | | Filter by Date/Subject | Add filters in the Gmail node settings. | | Change Time Zone | Edit timeZone in the Code node. | | Add More Email Fields | Modify the Set node to include more fields. | | Change File Format | Use a different format in the Convert to File node. | | Rename Output File | Adjust the name in the Google Drive node. | | Change Upload Folder | Set a different folderId in the Google Drive node. | 🚀 Deployment Tips Schedule the Workflow**: Replace Manual Trigger with a Cron node. Avoid Duplicates**: Store email IDs and skip duplicates using conditional logic. Security**: Use environment variables for sensitive credentials. 🧪 Testing Steps Manually trigger the workflow. Verify email data is parsed and formatted. Confirm CSV is generated correctly. Ensure the file is uploaded to Google Drive. 🧰 Requirements Connected Gmail and Google Drive OAuth2 credentials. n8n instance (self-hosted or cloud). Required nodes available in the n8n environment. > 💡 Need more features? You can add: > - Error handling > - Slack/Email notifications > - Conditional filters > - Google Sheets integration instead of Drive

Conference Feedback Collection and OneDrive Logging Workflow This n8n workflow is designed to collect feedback through a web form, log the responses into an Excel file stored in Microsoft OneDrive, and notify the support team via email. 🧭 Overall Goal To collect user feedback from a web form, structure the data, log it into a OneDrive Excel file, and notify support via Outlook email. 🔄 Workflow Breakdown 1. Form Submission (On form submission) Node Type**: formTrigger Purpose**: Captures user feedback via a web form. Form Fields**: Full Name (Required) Email (Required) Company Name Job Title How did you hear about the conference? (Required) Overall experience rating (Required) Favorite sessions/speakers Relevance to interests/work (Required) Networking opportunities (Required) Suggestions for improvement Future topics/speakers Willingness to attend again (Required) Additional comments Contact permission (Required) Access URL**: /webhook/feedback (or /webhook-test/feedback during testing) 2. Parse Data (Set) Purpose**: Renames form fields to snake_case. Output**: Structured JSON with renamed fields. 3. Sample File (Convert to File) Purpose**: Generates a file name reference for search. Filename**: test-n8n-feedback-form-data.xlsx 4. Search Document (Microsoft OneDrive) Purpose**: Searches OneDrive for the specified Excel file. Query**: test-n8n-feedback-form-data.xlsx 5. Extract File ID (Code) Purpose**: Extracts the ID of the file from the search result. Output**: { "id": "someFileId" } or { "id": null } 6. Check File Existence (If) Purpose**: Branch logic based on file existence. Condition**: If id exists. 7. Build Sheet Data (Set) Purpose**: Prepares the data to match the Excel column headers. Only Runs If**: File was found. 8. Append Data to Excel (Microsoft Excel) Purpose**: Appends the new feedback as a row. Workbook ID**: {{ $('Code').item.json.id }} Worksheet Name**: Sheet1 Mode**: Auto-map from input fields 9. Notify Support (Microsoft Outlook) Purpose**: Sends a notification email with key feedback details. To**: test@gmail.com Subject**: "New Feedback Submission Received" Body**: Includes key details from submission 10. End Workflow (NoOp) Purpose**: Marks logical end of the workflow. 📝 Sticky Notes ✅ Upload Target Excel File First: Ensure the Excel file exists in OneDrive. 📝 Filename Consistency: Filename should match in "Sample File" and "Search Document" nodes. 📧 Customize Email Content: Update "Notify Support" node with your desired message and recipient. 🔧 Customization Guide 🧾 Form Customization Change form title, description, fields, or path. 🧪 Parsing Logic Update field mappings if form labels change. 📁 Excel File Settings Filename must match your actual OneDrive file. Worksheet name and column headers must match in "Build Sheet Data". 📬 Email Settings Update subject and body using variables like {{ $('Parse Data').item.json.full_name }}. ❗ Error Handling Tips Adjust email content based on file presence. Add an "Error Trigger" for advanced error management. 🔁 Alternatives and Extensions Use Google Sheets, Airtable, or databases instead of OneDrive/Excel. Add Slack or SMS notifications. 📌 Use Cases Post-event Feedback CSAT Surveys Employee Feedback Bug Reporting Lead Capture Contact Forms Webinar Registration 🔐 Required Credentials 1. Microsoft OneDrive (OAuth2) Used by**: "Search Document" Credential Name**: Microsoft Drive account 2. Microsoft Excel (OAuth2) Used by**: "Append Data" Credential Name**: Microsoft Excel account 3. Microsoft Outlook (OAuth2) Used by**: "Notify Support" Credential Name**: Outlook 0Auth2 ❤️ Made with n8n by Akhil

This n8n workflow template uses community nodes and is only compatible with the self-hosted version of n8n. Restore n8n Credentials from Google Drive Backup This template enables you to restore your n8n credentials from a backup file in Google Drive. It's an essential companion to a credential backup workflow, ensuring you can recover your setup in case of data loss, instance migration, or disaster recovery. The workflow intelligently checks for existing credentials to prevent accidental overwrites of credentials with the same name that are already present. This workflow is manually triggered. We recommend you use this restore workflow in conjunction with a backup solution like our "Auto Backup Credentials to Google Drive" template. For more powerful n8n templates, visit our website or contact us at AI Automation Pro. We help your business build custom AI workflow automation and apps. Who is this for? This workflow is for n8n administrators and users who have backed up their n8n credentials to Google Drive (e.g., using a companion backup template) and need to restore them to the same or a different n8n instance. It's crucial for those managing self-hosted instances. What problem is this workflow solving? / use case If an n8n instance becomes corrupted, needs to be migrated, or if credentials are accidentally deleted, a manual re-creation of all credentials can be extremely time-consuming and error-prone. This workflow automates the restoration process from a known backup, saving significant time and ensuring accuracy. It's particularly useful for: Disaster recovery. Migrating n8n instances. Quickly setting up a new n8n instance with existing credentials. What this workflow does The workflow is manually triggered and performs the following operations: Fetch Current Credentials: An "On Click Trigger" starts the process. It executes the command npx n8n export:credentials --all --decrypted via the "Execute Command Get All Credentials" node to get a list of all credentials currently in your n8n instance. This list is then processed by "JSON Formatting Data" and "Aggregate Credentials" nodes to extract just the names of existing credentials for comparison. Download Backup File from Google Drive: The "Google Drive Get Credentials File" node searches your Google Drive for the n8n_backup_credentials.json file. The "Google Drive Download File" node then downloads the found file. Process Backup Data: The "Convert Files To JSON" (an Extract From File node) converts the downloaded file content, expected to be JSON, into a usable JSON object. "Split Out" nodes then process this data to handle individual credential entries from the backup file. Loop and Restore Credentials: The "Loop Over Items" (a SplitInBatches node) iterates through each credential from the backup file. Duplicate Check: For each credential, an "IF" node ("Check For Skipped Credentials") checks two conditions using an OR combinator: If the credential name from the backup ($('Loop Over Items').item.json.name) is empty. If a credential with the same name already exists in the current n8n instance (by checking against the list from the "Aggregate Credentials" node). Conditional Restore: If the credential name is NOT empty AND it does NOT already exist (i.e., the conditions in the IF node are false), the workflow proceeds to the "Restore N8n Credentials" node (an n8n API node). This node uses the name, type, and data for each new credential from the backup file to create it in the n8n instance. Credentials with empty names or those already present are skipped as they take the true path of the IF node, which loops back. A "Wait" node introduces a 1-second delay after each restoration attempt, to prevent API rate limiting before looping to the next item. Step-by-step setup n8n Instance Environment (for current credentials check): The n8n instance must have access to npx and n8n-cli for the "Execute Command Get All Credentials" node to function. Google Drive Credentials: Configure the "Google Drive Get Credentials File" and "Google Drive Download File" nodes with your Google OAuth2 credentials. n8n API Credentials: Configure the "Restore N8n Credentials" node with your n8n API credentials. This API key needs permissions to manage credentials. Backup File Name: The workflow is configured to search for a file named n8n_backup_credentials.json in the "Google Drive Get Credentials File" node. If your backup file has a different name or you want to specify a path, update the "Query String" parameter in this node. How to customize this workflow to your needs Backup File Location/Query:** Modify the "Google Drive Get Credentials File" node parameters if your backup file is in a specific folder, has a different naming convention, or if you want more specific query logic. Overwrite Logic:** The current workflow skips existing credentials by name. If you need to update/overwrite existing credentials, you would need to modify the logic in the "Check For Skipped Credentials" (IF) node and potentially use an "update" operation in the "n8n" API node if available for credentials (note: updates often require the credential ID, which might not be in the backup file). Notifications:** Add notification steps (e.g., Email, Slack) to report on the success or failure of the restoration process, and to list which credentials were restored or skipped. Selective Restore:** To restore only specific credentials, you could add a filter step after "Split Out1" or modify the IF condition in "Check For Skipped Credentials" to check for particular credential names or types from the backup file. Error Handling:** Implement more robust error handling for API errors (e.g., from the n8n API node or Google Drive nodes), file not found issues, or problems during command execution. Important Note on Credential Security Decrypted Backup File:** This workflow assumes the n8n_backup_credentials.json file contains decrypted credential data, typically created by a companion backup workflow. Execution Environment:** The "Execute Command Get All Credentials" node requires npx n8n-cli access on the server running n8n.

Tags*: Sustainability, Business Travel, Carbon Emissions, Flight Tracking, Carbon Interface API Context Hi! I’m Samir — a Supply Chain Engineer and Data Scientist based in Paris, and founder of LogiGreen Consulting. I help companies monitor and reduce their environmental footprint by combining AI automation, carbon estimation APIs, and workflow automation. This workflow is part of our sustainability reporting initiative, allowing businesses to track the CO₂ emissions of employee flights. > Automate carbon tracking for your business travel with AI-powered workflows in n8n! 📬 For business inquiries, feel free to connect with me on LinkedIn Who is this template for? This workflow is designed for travel managers, sustainability teams, or finance teams who need to measure and report on emissions from business travel. Let’s imagine your company receives a flight confirmation email: The AI Agent reads the email and extracts structured data, such as flight dates, airport codes, and number of passengers. Then, the Carbon Interface API is called to estimate CO₂ emissions, which are stored in a Google Sheet for sustainability reporting. How does it work? This workflow automates the end-to-end process of tracking flight emissions from email to CO₂ estimation: 📨 Gmail Trigger captures booking confirmations 🧠 AI Agent extracts structured data (airports, dates, flight numbers) ✈️ Each flight leg is processed individually 🌍 Carbon Interface API returns distance and carbon emissions 📄 A second Google Sheet node appends the emission data for reporting Steps: 💌 Trigger on new flight confirmation email 🧠 Extract structured trip data using AI Agent (flights, airports, dates) 📑 Store flight metadata in Google Sheets 🧭 For each leg, call the Carbon Interface API 📥 Append distance, CO₂ in kg, and timestamp to the flight row What do I need to get started? You’ll need: A Gmail account receiving SAP Concur or travel confirmation emails A Google Sheet to record trip metadata and CO₂ emissions A free Carbon Interface API key Access to OpenAI for parsing the email via AI Agent A few sample flight confirmation emails to test Next Steps 🗒️ Use the sticky notes in the n8n canvas to: Add your Gmail and Carbon Interface credentials Send a sample booking email to your inbox Verify that emissions and distances are correctly added to your sheet This template was built using n8n v1.93.0 Submitted: June 7, 2025

Do you want to check the SSL certificate expiration dates of your customers or servers? This workflow gets information of an SSL certificate using the uProc Get Certificate by domain tool. You can use this workflow to query SSL certificates in bulk and send alarms when any certificate has expired. You need to add your credentials (Email and API Key - real -) located at Integration section to n8n. You can replace "Create Domain Item" with any integration containing a domain, like Google Sheets, MySQL, or Zabbix server. Every "uProc" node returns the next fields per every analyzed SSL certificate: issuer: Contains the issuer. provider: Contains the provider. valid_from: Contains the start date. valid_to: Contains the end date. serial_number: Contains the serial number. type: Contains if supports one or multiple domains. protocol: Contains the protocol. valid: Contains its validity. domains: Contains all domains and subdomains supported. An "IF" node detects if the certificate is valid or not. Finally, the workflow sends an alarm to a Telegram channel to know if the certificate has expired.

This n8n workflow automates the handling of incoming emails. It detects and filters out spam, searches a knowledge base (FAQ) stored in a Pinecone vector database, and sends a reply using Gmail — all powered by an AI model (GPT-4o mini). How It Works Receiving Emails The Gmail Trigger node checks a Gmail inbox every hour. When a new email arrives, it starts the workflow. Fetching Full Email Content The get_message node retrieves all the details of the message: sender, subject, text, message ID, etc. Spam Filtering The Spam checker node uses GPT-4o mini to classify the email as either "spam" or "no spam". It detects not only classic spam but also automated messages (e.g. from Google or Microsoft). If marked as "spam", the workflow ends and nothing is processed. Conditional Filter The If node checks the spam result. Only "no spam" emails proceed to the AI Agent. AI-Based Reply The AI Agent node generates a response based on: The email content A system prompt defining the assistant’s behavior (polite, professional, under the name “Total AI Solutions”) Information retrieved from the Pinecone Vector Store, which contains FAQs The AI is instructed to always check the vector store before replying. The AI prepares both the subject and the body of the reply. Sending the Reply The Gmail node sends the reply to the original sender. It uses the original email's ID to keep the thread intact. Language Model The OpenAI Chat Model node provides GPT-4o mini as the language engine for generating responses. Memory Support The Simple Memory node maintains short-term context, helpful in multi-turn conversations. Knowledge Base (FAQ) The Pinecone Vector Store node connects to a Pinecone index (faqmattabott) containing vectorized FAQ content. Vectors are created using the Embeddings OpenAI node.

💡 How It Works: ⏰ Triggers daily at 6:00 AM 📊 Fetches one random question from your Google Sheet 🧠 Formats question, options, correct answer, and explanation 📤 Sends it to: 📧 Email 💬 Telegram (via Bot) 📱 WhatsApp/SMS (via Twilio) 🔧 What You Need to Configure: YOUR_GOOGLE_SHEET_ID → your sheet with columns: question, optionA, optionB, optionC, optionD, correctAnswer, explanation Email credentials (SMTP) Telegram Bot Token & Chat ID Twilio phone numbers and credentials