The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Sara — AI Grocery Ordering Agent (WhatsApp Backend)
An end-to-end AI grocery ordering backend on WhatsApp, built with n8n.
What it does:
- 3 AM price scraper — daily cron scrapes prices from Othaim, Panda, Sary, Amazon, and Noon, cleans them via LLM, and updates the price database
- Vision-to-JSON ordering - customers send a photo of their shopping list; GPT-4o vision extracts the items and matches each against the database for the lowest price (unit vs bulk).
- Dialect-friendly replies in seconds - answers in friendly Gulf Arabic dialect, always under 5 seconds.
- Order tracking - every order is logged to Google Sheets in real time with full status (ordering → order_notified).
- Instant owner notification - the store owner gets the order on Whats App the moment it's confirmed.
- Payment webhooks - Tap/Moyasar-ready for subscription activations, idempotent (no double charges).
- Delivery flow - placed → preparing → on the way → delivered, closed with a customer rating.
Try the live demo : https://n8n.yestisio.store/webhook/grocery-demo-sara/chat
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
I ran a session with my team on how to build a team of AI agents, and how to treat them so they actually deliver.
What we've seen running this setup on client work:
→ Agents running 24/7
→ 3B+ tokens in 6 days
→ A 2-week milestone done in 3 days
The 5 things I taught the team:
Treat agents like teammates, not software.
Give them a clear goal, the right context and tools they're comfortable with.
Tell them the goal, never the solution.
Let the agents propose the options. You make the call.
Talk to one agent, not ten.
A central PM agent takes the goal and coordinates the rest.
Solve today's problem.
Don't build the perfect agent on day one. Start small and let the team grow with the work.
Don't be the bottleneck.
Review at milestones, not every task.
For clients, this changes the pace. My job is understanding the problem and making the decisions. The agents handle the execution.
Highlights from the session 🎥
Building something and want to move faster with an AI-first team? Let's talk.
AI WhatsApp Customer Support Agent built with n8n, OpenAI, and Riwhap API. It automatically reads customer messages via Webhook, fetches data from Google Sheets, uses AI with chat memory to generate smart replies, and sends answers directly to WhatsApp.
AI AutomationBusiness Workflow AutomationLangFlowN8NZapierAI Chatbot DevelopmentAI Agent DevelopmentGoogle SheetsOpenAI
I'd route unanswered Sheets lookups to a person and pause automated replies for that conversation. How do you stop the agent and a human from answering the same WhatsApp message?
WhatsApp AI assistant for an energy company's employees. It answers questions from company documents (RAG with Azure OpenAI and Cognitive Search), adds source links, verifies who is asking before answering and understands voice messages. Python/Flask, Twilio, PostgreSQL, Docker.
