Loading page
Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers in technology companies who want to automate ingestion of product documentation and enable AI-driven, retrieval-augmented question answering via WhatsApp. What problem is this workflow solving? Support agents often spend too much time manually searching through lengthy documentation, leading to inconsistent or delayed answers. This solution automates importing, chunking, and indexing product manuals, then uses retrieval-augmented generation (RAG) to answer user queries accurately and quickly with AI via WhatsApp messaging. What these workflows do Workflow 1: Document Ingestion & Indexing Manually triggered to import product documentation from Google Docs. Automatically splits large documents into chunks for efficient searching. Generates vector embeddings for each chunk using OpenAI embeddings. Inserts the embedded chunks and metadata into a MongoDB Atlas vector store, enabling fast semantic search. Workflow 2: AI-Powered Query & Response via WhatsApp Listens for incoming WhatsApp user messages, supporting various types: Text messages: Plain text queries from users. Audio messages: Voice notes transcribed into text for processing. Image messages: Photos or screenshots analyzed to provide contextual answers. Document messages: PDFs, spreadsheets, or other files parsed for relevant content. Converts incoming queries to vector embeddings and performs similarity search on the MongoDB vector store. Uses OpenAI’s GPT-4o-mini model with retrieval-augmented generation to produce concise, context-aware answers. Maintains conversation context across multiple turns using a memory buffer node. Routes different message types to appropriate processing nodes to maximize answer quality. Setup Setting up vector embeddings 1. Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index. 2. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries. 3. Ensure the index name matches the one configured in n8n (data_index). 4. See the example MongoDB search index template below for reference. Setting up chat 1. Authenticate the WhatsApp node with your Meta account credentials to enable message receiving and sending. 2. Connect the MongoDB collection containing embedded product documentation to the MongoDB Vector Search node used for similarity queries. 3. Set up the system prompt in the Knowledge Base Agent node to reflect your company’s tone, answering style, and any business rules, ensuring it references the connected MongoDB collection for context retrieval. Make sure Both MongoDB nodes (in ingestion and chat workflows) are connected to the same collection with: An embedding field storing vector data, Relevant metadata fields (e.g., document ID, source), and The same vector index name configured (e.g., data_index). Search Index Example: { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } }
by NovaNodeDocument-Aware WhatsApp AI Bot for Customer Support Google Docs-Powered WhatsApp Support Agent 24/7 WhatsApp AI Assistant with Live Knowledge from Google Docs Description Template Smart WhatsApp AI Assistant Using Google Docs Help customers instantly on WhatsApp using a smart AI assistant that reads your company’s internal knowledge from a Google Doc in real time. Built for clubs, restaurants, agencies, or any business where clients ask questions based on a policy, FAQ, or services document. How it works Users send free-form questions to your WhatsApp Business number (e.g. “What are the gym rules?” or “Are you open today?”) The bot automatically reads your company’s internal Google Doc (policy, schedule, etc.) It merges the document content with today’s date and the user’s question to craft a custom AI prompt The AI (Gemini or ChatGPT) then replies back on WhatsApp using natural, helpful language All conversations are logged to Google Sheets for reporting or audit > Bonus: The AI even understands dates inside the document and compares them to today’s date — e.g. if your document says “Closed May 25 for 30 days,” it will say “We're currently closed until June 24. Set up steps 1. Connect your WhatsApp Cloud API account (Meta) 2. Add your Google account and grant access to the Doc containing your company info 3. Choose your AI model (ChatGPT/OpenAI or Gemini) 4. Paste your document ID into the Google Docs node 5. Connect your WhatsApp webhook to Meta (only takes 5 minutes) 6. Done — start receiving and answering customer questions! > Works best with free-tier OpenAI/Gemini, Google Docs, and Meta's Cloud API (no phone required). Everything is modular, extensible, and low-code. Customization Tips Change the Google Doc anytime to update answers — no retraining needed Add your logo and business name in the AI agent’s “System Prompt” Add fallback routes like “Escalate to human” if the bot can't help Clone for multiple brands by duplicating the workflow and swapping in new docs Need Help Setting It Up? If you'd like help connecting your WhatsApp Business API, setting up Google Docs access, or customizing this AI assistant for your business or clients… I offer setup, branding, and customization services: WhatsApp Cloud API setup & verification Google OAuth & Doc structure guidance AI model configuration (OpenAI / Gemini) Branding & prompt tone customization Logging, reporting, and escalation logic Just send a message via: Email: tharwat.elsayed2000@gmail.com WhatsApp: +20 106 180 3236
by Tharwat MohamedYoutube Explanation: https://youtu.be/KgmNiV7SwkU This n8n workflow is designed to automate the initial intake and scheduling for a law firm. It's split into two main parts: 1. New Inquiry Handling: Kicks off when a potential client fills out a JotForm, saves their data, and sends them an initial welcome message on WhatsApp. 2. Appointment Scheduling: Activates when the client replies on WhatsApp, allowing an AI agent to chat with them to schedule a consultation. Here’s a detailed breakdown of the prerequisites and each node. ** Prerequisites Before building this workflow, you'll need accounts and some setup for each of the following services: JotForm JotForm Account: You need an active JotForm account. A Published Form: Create a form with the exact fields used in the workflow: Full Name, Email Address, Phone Number, I am a..., Legal Service of Interest, Brief Message, and How Did You Hear About Us?. API Credentials: Generate API keys from your JotForm account settings to connect it with n8n. Google Google Account: To use Google Sheets and Google Calendar. Google Sheet: Create a new sheet named "Law Client Enquiries". The first row must have these exact headers: Full Name, Email Address, Phone Number, client type, Legal Service of Interest, Brief Message, How Did You Hear About Us?. Google Calendar: An active calendar to manage appointments. Google Cloud Project: Service Account Credentials (for Sheets): In the Google Cloud Console, create a service account, generate JSON key credentials, and enable the Google Sheets API. You must then share your Google Sheet with the service account's email address (e.g., automation-bot@your-project.iam.gserviceaccount.com). OAuth Credentials (for Calendar): Create OAuth 2.0 Client ID credentials to allow n8n to access your calendar on your behalf. You'll need to enable the Google Calendar API. Gemini API Key: Enable the Vertex AI API in your Google Cloud project and generate an API key to use the Google Gemini models. WhatsApp Meta Business Account: Required to use the WhatsApp Business Platform. WhatsApp Business Platform Account: You need to set up a business account and connect a phone number to it. This is different from the regular WhatsApp or WhatsApp Business app. API Credentials: Get the necessary access tokens and IDs from your Meta for Developers dashboard to connect your business number to n8n. PostgreSQL Database A running PostgreSQL instance: This can be hosted anywhere (e.g., AWS, DigitalOcean, Supabase). The AI agent needs it to store and retrieve conversation history. Database Credentials: You'll need the host, port, user, password, and database name to connect n8n to it. Node-by-Node Explanation The workflow is divided into two distinct logical flows. Flow 1: New Client Intake from JotForm This part triggers when a new client submits your form. 1. JotForm Trigger What it does: This is the starting point. It automatically runs the workflow whenever a new submission is received for the specified JotForm (Form ID: 252801824783057). Prerequisites: A JotForm account and a created form. 2. Append or update row in sheet (Google Sheets) What it does: It takes the data from the JotForm submission and adds it to your "Law Client Enquiries" Google Sheet. How it works: It uses the appendOrUpdate operation. It tries to find a row where the "Email Address" column matches the email from the form. If it finds a match, it updates that row; otherwise, it appends a new row at the bottom. Prerequisites: A Google Sheet with the correct headers, shared with your service account. 3. AI Agent What it does: This node crafts the initial welcome message to be sent to the client. How it works: It uses a detailed prompt that defines a persona ("Alex," a legal intake assistant) and instructs the AI to generate a professional WhatsApp message. It dynamically inserts the client's name and service of interest from the Google Sheet data into the prompt. Connected Node: It's powered by the Google Gemini Chat Model. 4. Send message (WhatsApp) What it does: It sends the message generated by the AI Agent to the client. How it works: It takes the client's phone number from the data (Phone Number column) and the AI-generated text (output from the AI Agent node) to send the message via the WhatsApp Business API. Prerequisites: A configured WhatsApp Business Platform account. --- Flow 2: AI-Powered Scheduling via WhatsApp This part triggers when the client replies to the initial message. 1. WhatsApp Trigger What it does: This node listens for incoming messages on your business's WhatsApp number. When a client replies, it starts this part of the workflow. Prerequisites: A configured WhatsApp Business Platform account. 2. If node What it does: It acts as a simple filter. It checks if the incoming message text is empty. If it is (e.g., a status update), the workflow stops. If it contains text, it proceeds to the AI agent. 3. AI Agent1 What it does: This is the main conversational brain for scheduling. It handles the back-and-forth chat with the client. How it works: Its prompt is highly detailed, instructing it to act as "Alex" and follow a strict procedure for scheduling. It has access to several "tools" to perform actions. Connected Nodes: Google Gemini Chat Model1: The language model that does the thinking. Postgres Chat Memory: Remembers the conversation history with a specific user (keyed by their WhatsApp ID), so the user doesn't have to repeat themselves. Tools: Know about the user enquiry, GET MANY EVENTS..., and Create an event. 4. AI Agent Tools (What the AI can do) Know about the user enquiry (Google Sheets Tool): When the AI needs to know who it's talking to, it uses this tool. It takes the user's phone number and looks up their original enquiry details in the "Law Client Enquiries" sheet. GET MANY EVENTS... (Google Calendar Tool): When a client suggests a date, the AI uses this tool to check your Google Calendar for any existing events on that day to see if you're free. Create an event (Google Calendar Tool): Once a time is agreed upon, the AI uses this tool to create the event in your Google Calendar, adding the client as an attendee. 5. Send message1 (WhatsApp) What it does: Sends the AI's response back to the client. This could be a confirmation that the meeting is booked, a question asking for their email, or a suggestion for a different time if the requested slot is busy. How it works: It sends the output text from AI Agent1 to the client's WhatsApp ID, continuing the conversation.
by iamvaar