Handle WhatsApp sales queries with GPT-4, Supabase, and a product catalog

Name: Handle WhatsApp sales queries with GPT-4, Supabase, and a product catalog
Availability: InStock
Author: Shadrack

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Overview

How it works

An AI-powered sales agent on WhatsApp that handles product inquiries using your Supabase knowledge base and n8n catalog. Customers can send text, voice notes, or images to ask about products, pricing, and specs. The agent responds with detailed answers, product images, and FAQs, creating a complete self-service sales experience. (I primarily designed this for furniture business, consider tailoring it)

Setup steps

Connect Supabase credentials for your knowledge base and FAQs Configure n8n tables with your product catalog (prices, descriptions, image links) Set up WhatsApp Business API integration Add your product categories and common queries to the AI context Test with sample product questions and image uploads

Customization tips

Structure your catalog tables with clear columns (SKU, price, description, image_url) Add industry-specific terminology to the AI prompt Create templated responses for common FAQs to ensure consistency Enable voice-to-text transcription for better voice note handling Add product recommendation logic based on customer queries Set up image recognition for customers sending product photos to identify items

Shadrack

7 workflows

Complexity

advanced

Published 05 Feb 2026

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/13220/13220.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Automate WhatsApp lead capture and replies with Whapi, Ollama and Sheets

Receive WhatsApp messages via Whapi, generate AI replies with a local Ollama model, log conversations in Google Sheets, and auto-capture leads — all without touching a cloud LLM. This n8n template builds a fully automated WhatsApp AI CRM using Whapi.cloud for messaging and Ollama for 100% local AI inference — no OpenAI costs, no data leaving your server. # How it works A Webhook node receives inbound WhatsApp messages from Whapi.cloud. A Code node extracts the sender's phone, name, message text, and filters out outbound/non-text messages. An IF node ensures only real inbound text messages from customers are processed. Google Sheets is used to fetch that customer's full conversation history, enabling memory across sessions. A Code node builds a full prompt — system instructions + conversation history + new message — passed to the AI model. Ollama (via LangChain LLM Chain node) generates a contextual reply using a local model (default: gemma3:1b). The user message and AI reply are each appended to Google Sheets as conversation history logs. A separate Google Sheets upsert captures or updates the lead record with phone and name. The AI reply is sent back to the customer via Whapi's HTTP API. # How to use Set up a Whapi.cloud account and connect a WhatsApp number. Point the webhook to your n8n webhook URL. Create a Google Sheet with a History tab (columns: Phone, Name, Role, Message, Timestamp) and a Leads tab (columns: Phone, Name, CreatedAt). Add your Google Sheets credentials and replace YOUR_GOOGLE_SHEET_ID in the relevant nodes. Run Ollama locally or on your server. Pull the model: ollama pull gemma3:1b. Update the model name in the Ollama node if using a different model. Customise the system prompt inside the Build AI Prompt node to match your business (real estate, support, bookings, etc.). Activate the workflow and send a WhatsApp message to test. # Requirements Whapi.cloud account (WhatsApp Business API) Ollama running locally or on a self-hosted server Google Sheets (with OAuth2 credentials connected in n8n) # Customising this workflow Switch AI models: Swap gemma3:1b for any Ollama-supported model like llama3, mistral, or phi3 depending on your hardware. Change the industry: Edit the system prompt in Build AI Prompt to serve any business — bookings, customer support, sales qualification, etc. Upgrade the CRM: Replace Google Sheets with Airtable, Notion, or a real CRM (HubSpot, Pipedrive) by swapping out the Sheets nodes. Add handoff logic: Insert a condition to escalate to a human agent if the message contains keywords like "speak to someone" or "human". Multi-language: The system prompt already instructs the AI to reply in the customer's language — no extra setup needed. # Who is this for It's designed for service businesses (real estate, consultants, agencies) that want to respond to inbound WhatsApp leads instantly, log conversations, and build a simple CRM — all from a single workflow.

View

Send multi-stage customer project emails from Google Sheets with Zoho ZeptoMail

Keep your clients informed at every stage of their project without lifting a finger. This workflow runs daily from Google Sheets and automatically sends four timed emails a Day 3 progress update, a Day 5 near-completion nudge, a feedback request on project completion, and a post-delivery upsell all via Zoho ZeptoMail. Each email is logged back to the sheet so no message ever sends twice. ## Who it's for Service businesses (resume writing, LinkedIn optimization, design, freelance agencies) that manage client orders in a Google Sheet and want structured follow-up without a CRM. ## How it works 1. A Schedule Trigger fires daily at 9 AM and reads all rows from your Google Sheet 2. Blank rows are filtered out; date variables are calculated dynamically 3. Four parallel branches check independently whether each email type is due: - **T+3** — progress update sent 3 days after the order date - **T+5** — near-completion update sent at day 5 (only after T+3 is confirmed sent) - **Feedback** — sent once the project status is marked Completed - **Upsell** — sent ~3 days after feedback, offering premium add-ons 4. Each qualifying row is looped one at a time, the email is sent via ZeptoMail, and the sheet is updated to prevent re-sends 5. After the upsell sends, the row status is set to **All Done** — permanently stopping all further checks for that customer ## Setup 1. Connect your **Google Sheets** and **Zoho ZeptoMail** credentials in n8n 2. Replace all `YOUR_RESOURCE_ID_HERE` placeholders in the Google Sheets nodes with your actual spreadsheet and sheet IDs 3. Set your sender address in all four email nodes (`YOUR_EMAIL_HERE`) 4. Update the feedback form link and booking link in the Feedback and Upsell email templates 5. Ensure your sheet has these columns: `Customer Name`, `Email`, `Project Type`, `Date Added`, `Status`, `T3_Email_Sent`, `T5_Email_Sent`, `Feedback_Email_Sent`, `Feedback_Email_Date`, `Upsell_Email_Sent`, `original_subject` ## Requirements - Self-hosted n8n instance (community node required) - Community node: `n8n-nodes-zohozeptomail` - Active Zoho ZeptoMail account with a configured mail agent

View

Send 10-day post-purchase WhatsApp offers with Odoo, OpenAI and Evolution API

What Problem Does It Solve? * Generic, automated retention messages often feel like spam and fail to engage returning customers. * Manually tracking which customers ordered exactly 10 days ago to send them tailored offers is extremely time-consuming. * Sending bulk promotional WhatsApp messages too quickly can result in phone number bans. * This workflow solves these issues by: - Automatically fetching customers from Odoo whose invoices are exactly 10 days old. - Using an AI Agent (OpenAI) to generate a highly personalized, warm Egyptian Arabic message for each customer. - Offering a targeted 10% extra discount to encourage repeat purchases via social media platforms. - Implementing a 1-minute "Wait" mechanism between messages to protect your WhatsApp account from being flagged. How to Configure It * Odoo Setup - Connect your Odoo credentials in n8n. - The workflow fetches invoices starting from April 2026. Adjust the date filter in the "Fetch 10-Day Old Invoices" node if needed. * OpenAI Setup - Add your OpenAI API key to the "Generate AI Message" node. - You can tweak the system prompt to match your specific brand voice or adjust the discount offer. * WhatsApp API Setup - This workflow uses the Evolution API. Update the URL and "apikey" in the "Send WhatsApp Discount" node with your specific instance details. How It Works * Every day at 10:01 AM, the schedule node triggers the workflow automatically. * It queries Odoo for all posted invoices exactly 10 days old and retrieves the corresponding customer contact details (Name and Phone). * It processes the customers one by one through a loop (Split In Batches). * For each customer, OpenAI generates a unique, friendly colloquial Arabic message calling them by their first name and offering a 10% discount. * The message explicitly directs the customer to claim the offer via social media messages, completely avoiding formal "terms & conditions" jargon. * The workflow sends the AI-generated text via WhatsApp and then pauses for 1 minute before processing the next customer. Customization Ideas * Change the AI prompt to offer different discounts based on the total amount the customer spent in their last order. * Add a condition to skip customers who have already made a new purchase within the last 10 days. * Switch the AI model to Claude or Gemini depending on your preference for Arabic copywriting. For more info [Contact Me](https://www.linkedin.com/in/khaledyasser01/)

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Handle WhatsApp sales queries with GPT-4, Supabase, and a product catalog

Workflow preview

Overview

How it works

Setup steps

Customization tips