Airtable and WhatsApp Business Cloud integration

This workflow automates multi-channel AI-driven sales engagement for lead qualification, service information delivery, and consultation booking. It integrates WhatsApp, Facebook Messenger, Instagram DM, and an n8n chat interface with a backend CRM (Airtable), a knowledge base (Supabase), and conversational AI (OpenAI), all orchestrated by n8n. Tools & Services Used Messaging Platforms: WhatsApp, Facebook Messenger, Instagram DM, n8n Built-in Chat AI Core & Processing: OpenAI (GPT-4o for main agent logic, Whisper for audio transcription) CRM & Data Management: Airtable (for initial WhatsApp lead lookup, lead form submissions, and as the backend for the crmAgent sub-workflow operations) Knowledge Base: Supabase (Vector Store for technical_and_sales_knowledge tool) Chat Memory: PostgreSQL (for the main AI Agent's conversation history) Orchestration & Automation: n8n (Self-hosted, utilizing Langchain community nodes) Calendar Service: Integrated via the calendarAgent sub-workflow CRM Service: Integrated via the crmAgent sub-workflow (interacting with Airtable) Workflow Overview This automation performs the following steps: Trigger: A new interaction is initiated through one of the following channels: A new message is received via the WhatsApp Trigger. A new message is received via the Facebook Trigger (Webhook). A new message is received via the Instagram Trigger (Webhook). A new message is received via the n8n Chat Trigger. Alternatively, a new lead is submitted via the Airtable Form Submitted Webhook. Channel-Specific Ingestion & Pre-processing: For WhatsApp: The system attempts to find an existing lead in Airtable using the sender's phone number. Incoming messages are routed by the Handle Message Types switch: Text messages are passed to the Edit Fields - chat1 node to prepare input for the AI Agent, including any found lead information. Audio messages are processed: the WhatsApp Business Cloud node gets the media URL, the HTTP Request node downloads the audio, OpenAI transcribes it to text, and Edit Fields - chat2 prepares this transcribed text and lead information for the AI Agent. Unsupported message types trigger the Reply To User1 node to send a notification that the message type cannot be processed. For Facebook Messenger: The system responds to webhook verification (Respond to Webhook - facebook get) and acknowledges new messages (Respond to Webhook - facebook post). The If is not echo - facebook node filters out messages sent by the page. The Sales Agent Demo - typing_on node sends a typing indicator. The Edit Fields - facebook node prepares the message text, sender ID, and Facebook-specific context for the AI Agent. For Instagram DM: The system responds to webhook verification (Respond to Webhook - instagram get) and acknowledges new messages (Respond to Webhook - instagram post). The If is not echo - instagram node filters out messages sent by the business account. The Edit Fields - instagram node prepares the message text, sender ID, and Instagram-specific context for the AI Agent. For n8n Chat: The Edit Fields - chat node prepares the user's input and session information for the AI Agent. Input Aggregation for AI Agent: Processed data from all active messaging channels (WhatsApp text/audio, Facebook, Instagram, n8n Chat) is funneled through the No Operation, do nothing node to the main AI Agent. AI Sales Conversation & Tool Utilization: The AI Agent (using OpenAI Chat Model - GPT-4o, and Postgres Chat Memory) engages the user according to its system prompt, aiming to qualify them for Paint Protection Film (PPF), Ceramic Coating, or Window Tint. The AI Agent uses the technical_and_sales_knowledge tool (which queries the Demo Supabase vector store via Embeddings OpenAI and OpenAI Chat Model1) to provide service details and answer questions. The AI Agent uses the crmAgent tool (a sub-workflow) to log contact details (Name, Email, service interest) and update opportunity statuses in Airtable. The AI Agent uses the calendarAgent tool (a sub-workflow) to book consultation appointments once preferred dates/times are provided. This occurs after contact details are logged in the CRM. Response Delivery: The AI Agent's final textual response is passed to the Switch node. The Switch node routes the response to the appropriate node for delivery on the original channel: Reply To User for WhatsApp. Facebook Graph API - Sales Agent Demo for Facebook Messenger. Instagram Graph API - smb.sales.agent.demo for Instagram DM. Output - chat for the n8n Chat interface. Airtable Form Submission Processing (Separate Branch): When the Airtable Form Submitted webhook receives data, the Airtable node fetches the full record. The Create Contact node creates a new contact in the Airtable 'Contacts' table. The Edit Fields - form node prepares data for a notification. The WhatsApp Business Cloud2 node sends a templated WhatsApp message to the lead, confirming their form submission.

Multi-Platform AI Sales Agent with RAG, CRM Logging & Appointment Booking This workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowledge base, and uses modular sub-workflows to manage your CRM in Airtable and book appointments in Google Calendar. Who Is It For? This solution is designed for service-based businesses that require a sophisticated, multi-channel lead management and appointment booking system. Agencies, consultants, and clinics** looking to automate lead qualification and booking across text and voice messages. Sales teams** needing a robust system that separates CRM and calendar logic for easier management and scalability. Advanced n8n users** who want a powerful, agent-based framework that can be easily customized and extended. Key Features & Workflow This system is composed of a parent workflow that orchestrates the conversation and calls specialized sub-workflows (agents) to perform specific tasks. Omni-Channel Engagement:* Greets and converses with leads naturally on Website Chat, WhatsApp, Instagram, Facebook, and Telegram*. Voice Message Transcription:* Automatically transcribes incoming audio/voice notes from WhatsApp and Telegram* into text, allowing the AI to understand and respond without manual intervention. RAG-Powered Intelligence:* The AI agent draws answers from your dedicated PostgreSQL Knowledge Base (RAG)*, providing accurate information about your services, pricing, and process. A built-in tool allows you to load new knowledge documents from Google Drive. Modular CRM Agent (Sub-Workflow):* When the conversation requires CRM actions (like creating a contact or updating an opportunity), the main agent calls a dedicated Airtable CRM sub-workflow* to handle the task. Modular Calendar Agent (Sub-Workflow):* To book appointments, the main agent calls a separate Google Calendar sub-workflow*, which manages event creation, updates, and deletions. What You'll Need This workflow framework requires credentials for the following services: An AI provider (OpenAI is used for the main agent, transcription, and embeddings). PostgreSQL** database with the pgvector extension (for RAG and chat memory). Airtable** account (for the CRM sub-workflow). Google Calendar** account (for the Calendar sub-workflow). Telegram Bot** credentials. A Meta Developer Account (for WhatsApp, Instagram & Facebook). (Optional) Google Drive for loading knowledge documents. (Optional) Google Gemini for embeddings. How to Set It Up This is a modular system. You must set up the sub-workflows first. Deploy Sub-Workflows: Create two new, separate workflows using the provided templates for the CRM Agent and the Calendar Agent. Configure the credentials (Airtable, Google Calendar) within those workflows, then save and activate them. Link Sub-Workflows in Main Workflow: Return to this main workflow. In the "CRM Agent" and "Consultation Agent" tool nodes, select the new workflows you just created from the dropdown list. Configure Main Credentials: Securely add the remaining credentials (OpenAI, PostgreSQL, Telegram, and your Meta App) in this main workflow. Personalize the AI Agent: In the "Update Agent Details" node, fill in your business name, the agent's persona name, and your key services to customize the AI's personality. Load Your Knowledge (Optional): To populate the RAG database, use the manual trigger path starting with "When clicking ‘Execute workflow’" to download a document from Google Drive and insert it into your PostgreSQL vector store. Activate: Configure your channel-specific details (e.g., Phone Number ID in WhatsApp nodes), save the workflow, and activate it. Demo CRM Table: View on Airtable

📌 Overview This n8n-powered workflow automates the entire lifecycle of real estate lead intake, qualification, routing, assignment, and reporting across multiple channels. It brings WhatsApp inquiries and website form submissions into a single intelligent system, where leads are processed conversationally using AI, deduplicated, normalized, assigned fairly to agents, logged into a centralized CRM, and reported on weekly. Designed specifically for real estate agencies, brokerages, and property teams, this system replaces manual follow-ups, spreadsheet chaos, and uneven agent assignments with a scalable, modular automation that can grow to include Facebook Lead Ads and Google Lead Forms without breaking downstream logic. 🧠 What It Does This workflow automates the full real estate lead pipeline. It: Collects inbound leads from WhatsApp and website forms. Uses AI to extract, validate, and structure lead information. Normalizes all leads into a consistent schema across sources. Detects and prevents duplicate leads (both within-run and CRM-level). Routes leads intelligently based on property interest. Assigns leads fairly using round-robin agent logic. Stores all leads and assignments in a centralized CRM. Sends automated notifications to agents and internal teams. Generates weekly lead, duplicate, and assignment reports. Is designed to be easily extended to Facebook Lead Ads and Google Lead Forms. 💡 Why This Workflow Real estate teams don’t struggle with demand — they struggle with lead management. This workflow was built to solve common real estate problems: Leads lost in WhatsApp chats Duplicate inquiries wasting agent time Uneven lead distribution across agents Manual CRM updates No visibility into weekly lead performance Instead of patching tools together, this workflow provides a single automated system that is reliable, extensible, and client-ready. 👤 Who It’s For This workflow is ideal for: Real estate agencies managing high WhatsApp and form lead inquiry volume Brokerages with multiple agents needing fair lead assignment Property developers handling inbound marketing leads Real estate lead generation teams Automation freelancers building reusable real estate systems ⚙️ How It Works 🧩 1. Lead Intake Workflow 🎯 Purpose Collect inbound leads from multiple channels and normalize them into a unified structure. 🛠 How It Works WhatsApp & Website Triggers Leads enter the system via: WhatsApp messages Website inquiry forms Lead Normalization Regardless of source, all leads are transformed into a common structure: First name, Last name, Phone number, Email, What is your budget range?, and others This ensures new channels (Facebook Lead Ads, Google Lead Forms) can be added later without changing core logic. 🧩 2. AI Lead Processing Workflow 🎯 Purpose Convert unstructured messages into clean, usable lead data. 🛠 How It Works AI Conversation Handling An AI agent processes inbound messages to: Extract missing details Validate lead intent Standardize property interest categories Data Validation Ensures required fields exist before moving forward. 🧩 3. Deduplication Workflow 🎯 Purpose Prevent duplicate leads from entering the system or being reassigned. 🛠 How It Works In-Execution Duplicate Check Prevents the same lead from being processed twice in a single run. CRM-Level Duplicate Detection Checks existing records using: Phone number Email Duplicate leads are flagged and excluded from reassignment while still logged for reporting. 🧩 4. Lead Routing & Agent Assignment Workflow 🎯 Purpose Assign leads fairly and intelligently to agents. 🛠 How It Works Property-Based Routing Leads are routed based on property type (e.g. Single-Family, Multi-Family, Condo). Round-Robin Assignment Agents are rotated automatically to ensure: Fair distribution No manual favoritism Predictable assignment logic 🧩 5. CRM Storage & Notifications Workflow 🎯 Purpose Keep all lead data centralized and notify the right people instantly. 🛠 How It Works CRM Logging (Airtable) Stores: Lead details** Assigned agent Source Deduplicates (Separate table) Timestamps Automated Notifications Sends alerts via: Email Slack So agents can respond immediately. 🧩 6. Weekly Reporting Workflow 🎯 Purpose Provide visibility into lead performance and system health. 🛠 How It Works Runs on a weekly schedule Generates summaries for: Total leads Duplicate leads Agent assignments Can be separated into its own workflow for scalability and reuse. 🛠 How to Set It Up Import the .json file into your n8n instance. Connect the required credentials: WhatsApp Trigger (Auth Connection) WhatsApp Business Cloud (Access Token) OpenAI API Key Airtable API Key (Access Token) Gmail Slack API Key (Access Token) Configure your data sources: Update the Airtable base and table names to match your CRM structure Real Estate Qualifier column names: First name | Last name | Phone number | Email | Location | Property Type | Timeframe | Payment Source | Pre Approved | Has Agent (Yes, No) | Lead (New, Contacted, Follow-up, Converted, Couldn't Convert) | Source | Assigned Agent | Assigned Time | Qualified (Yes, No) | Transcript | Summary Real Estate Qualifier Duplicate column names: First name | Last name | Phone number | Email | Location | Property Type | Timeframe | Payment Source | Pre Approved | Has Agent (Yes, No) | Source Customize business logic: Update agent pools and routing rules Adjust AI prompts if needed Review deduplication and reporting settings Activate the workflow: Click Publish to activate the workflow Send a test lead via WhatsApp or website form to confirm everything works 🎨 Customization Tips Add More Channels**: Plug in Facebook Lead Ads or Google Lead Forms — no restructuring needed. Routing Logic**: Customize routing by location, budget, or property category. CRM Expansion**: Add more fields (Notes, Follow-Up Status, Deal Stage). Reporting**: Extend weekly reports or connect to BI tools. Ads Integration**: Leads can optionally be passed into Facebook or Google Ads workflows after normalization. 📬 Contact For Enquiries: [email protected] Thank you for exploring this workflow!

🧠 How it works This workflow turns your website form into a fully automated AI Lead Qualification system. Whenever a new lead submits your form, the workflow: Receives the submission through a Webhook Cleans and normalizes the input fields Uses the AI Agent node to score and qualify the lead Saves all details (including AI analysis) into an Airtable CRM Automatically routes high-quality leads (score ≥ 7) Sends an instant Gmail notification Sends an AI-generated personalized auto-reply back to the lead This gives you a hands-free, intelligent front-door to your business — ensuring you only spend time on high-value opportunities. ⚙️ Set-up steps These steps help users configure the workflow quickly: Create a Webhook trigger – Copy the webhook URL and add it to your form tool (Tally, Typeform, Webflow, etc.). Prepare your Airtable base – Create a "Leads" table with fields for name, email, website, message, lead score, priority, use case, timeline, budget, and AI notes. Add the AI Agent node – Insert the provided System + User prompts – Enable Structured Output – Paste the JSON Schema included in the sticky note inside the workflow. Connect Airtable – Map the original form fields + AI Agent “output” fields to Airtable columns. Set up the Gmail node – Connect your Gmail account – Configure the notification email and auto-reply templates. Configure the IF node – Score ≥ 7 routes to the “Hot Lead” branch – Everything else is captured but not routed. Run a test submission – Verify that the workflow writes to Airtable – Confirm the Gmail notification + auto-reply are delivered – Adjust prompting if needed. All detailed explanations and prompt configurations are included inside the workflow through sticky notes for easy reference.