Uruguayan restaurant company
Customers order on WhatsApp in their own words, and the order shows up in the kitchen.
A multi-venue restaurant system that takes orders over WhatsApp, in development for a Uruguayan company.
At a glance
- customers order by chat and the AI builds the order
- Kitchen
- orders land on a board and move by status until delivery
- Branches
- each location has its own menu, orders and staff in one account
The problem
A Uruguayan company in the restaurant business asked us to build a system for restaurants. A small venue uses one tool for tables, another for delivery, a spreadsheet for the cash register and a phone for WhatsApp orders. The goal was to bring all of that into one system any venue could sign up for with nothing to install.
What we built
We built it as a monorepo with a NestJS API and a Next.js web app, on Supabase (Postgres, Auth and Realtime) with Drizzle. The API is organized by domain: orders, menu, tables, cash register, delivery, customers, staff, reports, invoicing and payments, among others. Each restaurant’s data stays isolated within the same platform.
The core of it is the WhatsApp bot: customers write their order in their own words, and a language model turns it into a real order that shows up at the venue in real time. Restaurant subscriptions are billed through Mercado Pago, files go to Cloudflare R2, and every change runs through continuous integration on GitHub Actions.
Before launch we ran a production-readiness audit and wrote a pilot plan for the bot.
Where it stands
We’re building it for that company and it’s still in development. No restaurants are running on it yet.