所有案例研究餐饮酒店

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.

4 分钟阅读更新于 2026-04-03基于 Claude Sonnet 4 / GPT-4o

The Real Problem

Jisoo runs a Korean fried chicken shop in Kingsland. The food is great -- her double-fried yangnyeom chicken has a 4.8 rating on Google and a loyal following. But 65% of her orders come through Uber Eats, and Uber Eats takes up to 30% commission on every order.

The maths is brutal. A customer orders NZD 30 worth of chicken and beer. Uber Eats takes NZD 9. After food cost (roughly NZD 10), Jisoo nets about NZD 11. On a busy month, she's paying NZD 2,000+ in delivery commissions alone. That's NZD 24,000 a year going to a platform, not to her business.

She's not alone. One NZ restaurant owner reported receiving only NZD 85 from NZD 300 in Uber Eats orders after commissions, adjustments, and fees. Another described the platforms as "a necessary evil" -- you need the visibility to get customers, but the economics hollow out your margins.

Korean fried chicken is especially delivery-dependent. Chimaek culture -- chicken and beer -- is fundamentally a delivery and takeaway experience. Customers order from the couch while watching Netflix. They're not walking into a restaurant; they're scrolling through an app. In New Zealand, the K-pop and Korean drama wave has driven massive interest in Korean food, and Korean fried chicken shops have multiplied across Auckland. Ko Ko Dak started in a garage and now operates 9+ stores processing 12 tonnes of chicken per month -- almost entirely driven by takeaway and delivery demand.

Jisoo knows her repeat customers. She recognises their names on the Uber Eats orders. They order the same thing every Friday night. But she has no way to contact them directly. Uber Eats owns the customer relationship. If Uber Eats raises commissions or changes the algorithm, Jisoo's business takes the hit and she can't do anything about it.

Why Existing Tools Don't Solve This

Building your own ordering website or app is expensive -- NZD 5,000-15,000 for a custom build, plus ongoing maintenance. Platforms like Bopple or Mr Yum offer white-label ordering, but they still charge monthly fees and per-order commissions (lower than Uber Eats, but not zero), and they don't solve the marketing problem of getting customers to switch from the app they already have open.

Some NZ restaurants have successfully moved to direct ordering -- Narm Thong Thai, Thai Niyom, and several Vietnamese restaurants run their own phone and web ordering. But they did it through years of building a local following. For a newer Korean fried chicken shop competing against Uber Eats' discoverability, the transition is harder.

The core problem isn't the ordering technology. It's convincing customers who already have Uber Eats on their phone to order directly instead. That requires a direct channel, a reason to switch, and an ordering experience that's at least as easy as tapping "reorder" on the app.

How AI Solves This

The AI creates a direct ordering channel via WhatsApp -- the app your customers already have, no download required -- and gives them a reason to use it.

The Transition: From Uber Eats to Direct

Every Uber Eats order that Jisoo fulfils gets a small card in the bag:

Love our chicken? Order direct and save 15%.

Scan this QR code to order on WhatsApp next time. Same chicken, same delivery -- but you save money and support us directly.

[QR Code]

When a customer scans the code and messages on WhatsApp, the AI handles the entire order:

Customer: "Hey, can I order for delivery to Grey Lynn?"

AI: "Hey! Absolutely. Here's tonight's menu:

Fried Chicken

  • Half yangnyeom (sweet chilli): NZD 16
  • Half garlic soy: NZD 16
  • Full combo (half-half): NZD 28
  • Whole original (8pc): NZD 26

Sides

  • Tteokbokki (rice cakes): NZD 12
  • KFC chips: NZD 8
  • Pickled radish: NZD 4

Drinks

  • Hite beer (500ml): NZD 8
  • Soju (original): NZD 14
  • Coke/Sprite: NZD 4

What would you like?"

Customer: "Full combo half-half, tteokbokki, and 2 Hite beers"

AI: "Great choices! Your order:

  • Full combo (half-half): NZD 28
  • Tteokbokki: NZD 12
  • 2x Hite beer: NZD 16
  • Subtotal: NZD 56
  • Delivery fee: NZD 5
  • Direct order discount: -NZD 8.40 (15% off food)
  • Total: NZD 52.60

Delivery to Grey Lynn -- estimated 35-40 minutes. Pay on delivery (cash or card) or I can send a payment link now. Which do you prefer?"

The AI knows the full menu, handles modifications ("extra sauce," "no spring onion"), calculates the direct-order discount, and confirms delivery time based on current kitchen load.

Repeat Customer Recognition

The AI remembers repeat customers:

Customer (returning): "Hey, same as last time please"

AI: "Welcome back! Last time you had the full combo half-half with tteokbokki and 2 Hite beers. Same again? That's NZD 52.60 delivered to Grey Lynn. Shall I put it through?"

This "reorder" experience is just as frictionless as the Uber Eats app -- but Jisoo keeps the full margin.

Weekend Upsell

On Friday and Saturday evenings, the AI proactively messages customers who've ordered before:

"Friday night chimaek? Your usual half-half combo is ready to go. This weekend's special: order a full combo and get a free tteokbokki. Reply 'ORDER' to get started."

This turns one-time Uber Eats customers into direct-ordering regulars.

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:

  • Connecting the AI ordering agent to WhatsApp Business so customers can order via chat
  • Integrating with your POS or kitchen display system so orders flow directly to the kitchen without manual re-entry
  • Setting up payment links (Stripe or bank transfer) for contactless payment
  • Building the repeat customer database so the AI remembers past orders and preferences
  • Configuring delivery zone rules, estimated times, and delivery fees based on distance

Here's our process:

  1. We map your current workflow -- We sit down with you and understand how orders currently flow through Uber Eats, your POS, and your kitchen.
  2. We build the connections -- Our developers write a custom program (an API connector) that lets the AI take orders, process payments, and send them to your kitchen. No manual data entry, no copy-pasting between apps.
  3. We test end-to-end -- We run test orders through the full cycle: WhatsApp order, kitchen confirmation, delivery dispatch, payment. Nothing launches until the whole chain works reliably.
  4. We maintain it -- When you change your menu, adjust prices, or add delivery zones, we update the system to match.

You don't need to be technical. We handle all the development -- you just tell us how your business runs, and we make the AI fit into that.

The Result

  • NZD 500-2,000/month saved in commissions -- every order moved from Uber Eats to direct saves 15-30% in platform fees
  • You own the customer relationship -- direct contact means you can reach regulars for promos, specials, and loyalty
  • Frictionless reordering -- repeat customers say "same as last time" and they're done
  • Higher average order value -- the AI suggests sides, drinks, and combo upgrades naturally during the conversation
  • Uber Eats becomes your billboard -- new customers discover you on the app, repeat customers order direct

What AI Can't Do Here

  • AI can't replace Uber Eats entirely -- you still need the platform for discovery and new customer acquisition
  • AI can't manage delivery logistics -- you need your own drivers or a delivery partner (e.g., a local courier arrangement)
  • AI can't prevent customers from choosing Uber Eats for convenience -- some will always prefer the app
  • AI can't handle complex order disputes or refunds -- those need a human conversation
  • The transition takes time -- expect 3-6 months to shift a meaningful percentage of orders to direct

Who This Is For

  • Korean fried chicken shops paying NZD 1,000+/month in delivery platform commissions
  • Any takeaway-heavy restaurant where repeat customers order the same thing regularly
  • Restaurants that recognise their Uber Eats customers by name but can't contact them directly
  • Owners who want to build a direct customer base instead of renting one from a platform
  • Delivery-dependent businesses looking to improve margins without raising prices

想为你的企业实现这个?

预约 45 分钟的工作流审查,我们将向你展示这如何应用于你的具体情况,无需任何承诺。

更多餐饮酒店案例研究

上了14小时班,还要回Google评价

AI如何起草引用具体菜品和反馈的个性化评价回复,让你的Google形象保持活跃,哪怕你已经累瘫了。

阅读案例研究

每个漏接的电话都是一笔丢失的预约

AI如何在用餐高峰期接听餐厅电话,处理订位、菜单问题和营业时间咨询,不需要把员工从餐厅叫走。

阅读案例研究

你的Instagram上个月的特价之后就没更新过了

AI如何根据你的每日特价、美食照片和活动生成每周社交媒体日历,让你的动态保持活跃,无需雇营销团队。

阅读案例研究

一个视频,五种语言,零翻译成本

一款AI工具,将一条宣传视频转换成英语、普通话、日语、韩语和印地语版本,配有母语级配音和口型同步。

阅读案例研究

你不知道每道菜实际花了你多少成本

AI如何把供应商发票变成实时食材成本追踪,让你在利润消失之前就看清毛利率。

阅读案例研究

同样的10个问题,一周被问50遍

AI如何在WhatsApp、Facebook和Google上处理重复的客户咨询,让你不用每天都打'是的,我们有无麸质选项'。

阅读案例研究

一小时内搞定带AI美食摄影的专业菜单

一款AI工具,输入你的菜品信息,生成精美排版的多语言菜单,每道菜都有逼真的美食图片。

阅读案例研究

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.

阅读案例研究

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.'

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究

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.

阅读案例研究