All Case StudiesHospitality

Thirty Cents of Every Dollar Goes to Uber Eats

How one Auckland Chinese restaurant built its own ordering channel and kept the margin -- without learning to code.

4 min readUpdated 2026-04-03Based on Claude Sonnet 4 / GPT-4o

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:

  1. 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.
  2. 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.
  3. 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.
  4. 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

Want This for Your Business?

Book a 45-minute workflow review and we'll show you exactly how this applies to your specific situation, no obligation, no fluff.

More Hospitality Case Studies

Replying to Google Reviews After a 14-Hour Shift

How AI drafts personalised review responses that reference specific dishes and feedback — so your Google presence stays active even when you're exhausted.

Read case study

Every Missed Call Is a Lost Booking

How AI answers your restaurant's phone during service — handling reservations, menu questions, and hours enquiries without pulling staff off the floor.

Read case study

Your Instagram Hasn't Been Updated Since Last Month's Special

How AI creates a weekly social media calendar from your daily specials, food photos, and events — keeping your feed alive without hiring a marketing team.

Read case study

One Video, Five Languages, Zero Translators

An AI tool that takes a single promo video and produces localized versions in English, Mandarin, Japanese, Korean, and Hindi with native voiceover and lip-sync.

Read case study

You Don't Know What Each Dish Actually Costs You

How AI turns supplier invoices into real-time food cost tracking — so you know your margins before they disappear.

Read case study

The Same 10 Questions, 50 Times a Week

How AI handles repetitive customer enquiries across WhatsApp, Facebook, and Google — so you stop typing 'Yes, we have gluten-free options' every day.

Read case study

A Professional Menu with AI Food Photography in Under an Hour

An AI tool that takes your menu items and generates a beautifully designed, multilingual menu with photorealistic food images for every dish.

Read case study

The Saturday Morning Catering Call You Never Answered

How AI captures corporate catering enquiries during your busiest rush -- so you stop losing $800 orders to the cafe down the road.

Read case study

The Menu Nobody Could Read

How AI bridges the language gap between Chinese restaurant kitchens and Kiwi customers -- turning 'What's Mapo Tofu?' into a $22 order instead of 'Just sweet and sour pork, thanks.'

Read case study

Raj and Priya Can't Answer the Phone During Dinner Rush

How AI takes every takeaway and catering call during your busiest hours -- so you stop losing orders while you're cooking.

Read case study

Fifteen Catering Enquiries Before Diwali. Three Replies Sent.

How AI qualifies catering leads, collects requirements, and prepares quotes -- so you never lose a wedding booking because you replied too late.

Read case study

Twenty Seats. Forty People Waiting. No System.

How AI turns a chaotic ramen shop queue into a smooth virtual waitlist -- so customers wait from the cafe next door instead of leaving.

Read case study

Forty Pieces of Salmon Nigiri in the Bin Every Night

How AI predicts exactly how much sushi to prepare each hour -- so you stop throwing profit in the bin at closing time.

Read case study

The Korean BBQ That Nearly Closed Its Dining Room

How AI handles bilingual bookings and guides first-time diners through Korean BBQ -- so you don't need to choose between answering phones and running service.

Read case study

Chimaek Without the Commission

How a Korean fried chicken shop built AI-powered direct ordering and stopped giving 30% of every delivery to Uber Eats.

Read case study

The Pho Shop That Stopped Feeding Uber

How a family-run Vietnamese restaurant built its own AI ordering channel and kept the 30% margin Uber Eats was taking.

Read case study

No Peanuts, No Problem

How AI gives every customer instant, accurate allergen information for every dish -- so your staff never have to guess about fish sauce or shrimp paste again.

Read case study

The Friday Night Phone Problem

How AI answers every call at a fish and chips shop during the Friday rush -- so two people can keep frying instead of one running to the phone.

Read case study

How an Independent Pizza Shop Fights Back Against Domino's

How AI phone ordering and smart upselling help a single-location pizza shop compete with chain-level technology -- without chain-level budgets.

Read case study

The Weekend That Books Itself

How AI handles bilingual hotpot reservations, manages the waitlist, and guides first-timers -- so your staff stay on the floor instead of the phone.

Read case study

The AYCE Profit Protector

How AI tracks consumption, predicts prep quantities, and protects margins at an all-you-can-eat BBQ restaurant -- without awkward waste penalties.

Read case study

The Monday Prawn Problem

How AI predicts exactly how much food to prepare for each buffet session -- so you stop throwing away $200 of prawns on quiet nights.

Read case study

The Tapioca Timing Problem

How AI tells your bubble tea shop exactly when to cook the next batch of pearls -- so you stop throwing away rubbery tapioca at closing time.

Read case study

One Photo, Four Platforms, Two Languages

How AI turns a single product photo into bilingual social media content for Instagram, TikTok, WeChat, and Xiaohongshu -- in minutes, not hours.

Read case study