---
name: al-397-set-up-and-run-your-restaurant-s-own-commission-free-onli
description: "Delivery apps take a commission on every order, but setting up your own ordering site usually means learning a dashboard full of settings. On Oct 29, 2026 Menuthere, a Kochi, India restaurant tech startup used by more than 1,000 restaurants in over 70 countries, launched Zao, an AI agent that lets owners set up and run their own zero-commission online ordering just by chatting. The owner types the restaurant's name, and Zao reads the menu from a photo or PDF of the paper menu, sets the store link, brand colour and logo, and has the ordering store ready when the chat ends; signup works in 10 languages. Afterwards an owner can type things like 'add a weekend offer on biryani', 'change the delivery charge' or 'make QR codes for 12 tables', and every change can be undone. Asked how to increase sales, it answers from the restaurant's own numbers. Menuthere says about a third of its restaurants' online orders come through their own websites, one in five through their own apps and the rest…"
---

# Set up and run your restaurant's own commission-free online ordering by chatting with an AI agent: send it a photo of your paper menu, then change prices, offers, hours and delivery areas in plain words

Delivery apps take a commission on every order, but setting up your own ordering site usually means learning a dashboard full of settings. On Oct 29, 2026 Menuthere, a Kochi, India restaurant tech startup used by more than 1,000 restaurants in over 70 countries, launched Zao, an AI agent that lets owners set up and run their own zero-commission online ordering just by chatting. The owner types the restaurant's name, and Zao reads the menu from a photo or PDF of the paper menu, sets the store link, brand colour and logo, and has the ordering store ready when the chat ends; signup works in 10 languages. Afterwards an owner can type things like 'add a weekend offer on biryani', 'change the delivery charge' or 'make QR codes for 12 tables', and every change can be undone. Asked how to increase sales, it answers from the restaurant's own numbers. Menuthere says about a third of its restaurants' online orders come through their own websites, one in five through their own apps and the rest through WhatsApp, and 52% of orders from signed-in customers came from repeat customers. The prompt below gets your menu and ordering rules ready for any direct-ordering tool.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Name, city, cuisine
- Menuthere / my website / WhatsApp ordering
- Your own material (text, notes or data)

## Instructions

Do the task below with the user's inputs in place of each [bracket].

Help me move more of my restaurant's orders off the delivery apps and onto my own direct ordering. Restaurant: [name, city, cuisine]. I've attached a photo or PDF of my menu. 1) Turn the menu into a clean table: category, dish, short description, sizes, price, and dietary tags; list anything you couldn't read instead of guessing. 2) Ask me for my delivery areas, delivery charge, minimum order, opening hours and pickup or dine-in options, then write them out as settings I can paste into my ordering tool ([Menuthere / my website / WhatsApp ordering]). 3) Suggest 3 simple offers for direct customers (e.g. a weekday combo or a loyalty reward) and show what each costs me per order at my food cost of [ ]%. 4) Write a short card for every table and takeaway bag telling customers how to order direct, plus a WhatsApp reply with the menu link. 5) Each week, when I paste my orders by channel (delivery apps, website, app, WhatsApp), show the share of direct orders and repeat customers and the commission I saved. Never publish a price or offer change without my OK.

## Safety checks (share these with the user)

- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records.
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Menuthere Zao, ChatGPT, Claude, WhatsApp
- Based on this real-world example: https://www.usareport.news/news/kochi-startup-menuthere-launches-zao-an-ai-agent-that-lets-restaurant-owners-set-up-and-run-zero-commission-online-ordering-just-by-chatting20261029165818/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-397-set-up-and-run-your-restaurant-s-own-commission-free-online/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/
