The Real Problem
Liang owns a Chinese restaurant in West Auckland. The food is good -- generous portions, authentic flavours, loyal local following. But 60% of his orders come through Uber Eats, and the numbers are devastating.
NZ Herald reported a West Auckland restaurant that received just NZD 85 from NZD 300 in Uber Eats orders. That's 28 cents retained from every dollar. Uber Eats charges up to 35% commission in New Zealand. For a Chinese restaurant operating on 3-5% margins, that commission doesn't just eat into profit -- it eliminates it entirely.
Liang does the maths every month. His Uber Eats orders generate around NZD 8,000 in gross sales. After Uber Eats takes its cut, he keeps roughly NZD 5,200. The NZD 2,800 that goes to the platform would be his entire monthly profit if he could keep it.
He's tried the obvious workarounds. He inflated Uber Eats prices by NZD 5-10 per dish -- a common practice that customers on Reddit openly complain about. He built a basic website with an online ordering page. But nobody uses it. Customers don't know it exists, and the ordering experience is clunky compared to the polished Uber Eats app they're used to.
The core problem is a double bind. Uber Eats brings customers, but the commission makes those customers unprofitable. His own website could be profitable, but he can't get customers to use it. And as a family operator whose first language is Mandarin, building and promoting a sophisticated direct ordering system is beyond his technical and English-language comfort zone.
Why Existing Tools Don't Solve This
Zero-commission platforms exist. Easy Eats (Wellington-based, 0% commission) and Order Meal NZ offer alternatives. But adoption among Chinese restaurant owners is low -- the platforms are English-first, the onboarding process requires technical setup, and there's no marketing support to actually drive customers to use them.
Building a custom ordering website through a developer costs NZD 5,000-15,000 and still doesn't solve the marketing problem. A beautiful ordering page means nothing if customers don't know it exists.
The real barrier isn't technology -- it's the gap between "having an ordering channel" and "getting customers to actually use it." That gap requires active customer redirection, a frictionless ordering experience, and communication in the languages your customers speak. No off-the-shelf platform delivers all three.
How AI Solves This
BestAI builds Liang a direct ordering channel powered by a bilingual AI chatbot on WhatsApp and his website. Customers order by chatting -- in English or Chinese -- and the AI handles the entire flow.
The Ordering Experience
A customer clicks the WhatsApp link on Liang's website:
Customer: "Hi, I want to order for pickup"
AI: "Hey! Here's what's popular tonight:
Chef's Picks:
- Kung Pao Chicken -- NZD 20
- Mapo Tofu -- NZD 18
- Salt & Pepper Squid -- NZD 22
- Beef Chow Fun -- NZD 19
Or I can send you the full menu. What are you in the mood for?"
Customer: "Kung pao chicken and two fried rice. Oh and can I get some spring rolls?"
AI: "Got it! Here's your order:
- Kung Pao Chicken -- NZD 20
- Fried Rice x2 -- NZD 24
- Spring Rolls (6pc) -- NZD 12
Total: NZD 56
Would you like to add anything else? Our Wonton Soup (NZD 14) goes really well with the Kung Pao Chicken.
Pickup time is about 25 minutes. Sound good?"
Customer: "Add the wonton soup. That's it."
AI: "Updated:
- Kung Pao Chicken -- NZD 20
- Fried Rice x2 -- NZD 24
- Spring Rolls (6pc) -- NZD 12
- Wonton Soup -- NZD 14
Total: NZD 70
Ready for pickup at 7:15pm. I'll send a message when it's ready. Name for the order?"
That NZD 70 order generates NZD 70 in revenue for Liang. On Uber Eats, it would generate NZD 45.
Chinese Language Support
The same flow works in Mandarin. A Chinese customer types:
"我想点外卖,两个宫保鸡丁,一个麻婆豆腐"
The AI responds in Chinese, confirms the order, and sends the same structured ticket to the kitchen -- in Chinese, because that's what the kitchen speaks.
The Redirect Strategy
Here's the critical piece: every Uber Eats bag that leaves Liang's kitchen includes a printed card with a QR code:
"Order direct next time -- same food, faster pickup, 10% off. Scan here."
The QR code opens Liang's WhatsApp ordering channel. The 10% discount is funded by the 35% commission he's no longer paying to Uber Eats -- he still comes out ahead by 25%.
Over time, repeat customers shift. They learn that ordering direct is faster (no Uber Eats wait time), cheaper (the 10% discount), and easier (a WhatsApp chat is simpler than navigating an app). The AI recognises returning customers and remembers their usual orders:
"Hey Sarah! Same as last time? Kung Pao Chicken, Fried Rice, and Wonton Soup -- NZD 52 with your direct order discount. Ready in 20 minutes?"
One tap to confirm. Faster than Uber Eats.
How We Set This Up
None of this works if the AI is just a standalone chatbot with no connection to your actual business. That's why BestAI builds a custom integration program -- a piece of software that bridges your AI assistant with the systems you already use.
For this kind of setup, that means:
- Building a bilingual AI ordering chatbot on WhatsApp and your website that takes orders in English or Chinese
- Creating a digital menu with pricing, categories, and smart add-on suggestions that the AI uses during ordering
- Setting up a kitchen notification system so orders appear instantly on a screen or printer in the language your kitchen staff work in
- Designing and printing QR code cards for every Uber Eats bag to redirect customers to the direct channel
- Building a returning customer system that recognises repeat orders and offers loyalty pricing
Here's our process:
- We map your current workflow -- We sit down with you and understand your menu, your Uber Eats volume, your kitchen workflow, and which customers are most likely to switch to direct ordering.
- We build the connections -- Our developers write a custom program (an API connector) that lets the AI take orders, notify your kitchen, and track repeat customers. No manual data entry, no copy-pasting between apps.
- We test end-to-end -- Every workflow gets tested with real orders before going live. We test in both English and Chinese to make sure nothing gets lost in translation.
- We maintain it -- When your menu prices change or you add seasonal dishes, we update the system to match.
You don't need to be technical. We handle all the development -- you just tell us your menu and we build the ordering experience around it.
The Result
- NZD 2,500+/month in saved commissions -- once 40-50% of delivery orders shift to direct ordering (realistic target within 6 months)
- Higher average order value -- AI add-on suggestions increase basket size by 10-15%
- Bilingual ordering -- Chinese and English customers both order in their preferred language
- Returning customer recognition -- repeat customers reorder in seconds, building loyalty to your restaurant instead of to Uber Eats
- Kitchen gets orders in Chinese -- no miscommunication from English-only platforms
What AI Can't Do Here
- AI won't handle delivery logistics -- you still need your own delivery drivers or a delivery-only service
- AI won't process payments directly -- customers pay on pickup or via a linked payment method you set up
- AI won't eliminate Uber Eats overnight -- platform dependency reduces gradually as direct orders grow
- AI can't force customers to switch -- the QR code strategy works over time, not instantly
- AI won't solve the underlying price war in the Chinese restaurant market -- it helps you keep more of what you earn
Who This Is For
- Chinese restaurant owners paying NZD 2,000+/month in delivery platform commissions
- Family-operated restaurants where English is a barrier to setting up online ordering
- Any restaurant where Uber Eats or DoorDash takes 30%+ of delivery revenue
- Restaurant owners who want to build direct customer relationships instead of renting them from a platform
