所有案例研究餐饮酒店

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.

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

The Real Problem

Somchai runs a Thai restaurant in Grey Lynn. He's been cooking Thai food for 20 years. He knows every ingredient in every dish by heart.

His staff don't.

Last month, a customer asked the new waitress whether the green curry contained shrimp paste. The waitress said she'd check. She went to the kitchen. Somchai was mid-service, three tickets deep. He said yes, it does. She went back and told the customer. The whole exchange took four minutes -- during which two other tables waited.

That's a good outcome. The bad outcome happened six months ago. A different staff member told a customer the pad thai was nut-free. It isn't -- the recipe includes crushed peanuts. The customer had a peanut allergy. Somchai caught it before the dish went out, but it was close. Too close.

Thai and Vietnamese cuisines are minefields for allergens. Fish sauce is in almost everything -- and it's a shellfish derivative. Shrimp paste hides in curry pastes and stir-fry sauces. Soy sauce contains gluten. Peanuts appear in pad thai, satay, and garnishes. Coconut is in curries, desserts, and drinks. Many of these ingredients aren't obvious from the dish name.

Somchai gets 5-10 allergen questions per service. On busy nights, more. Each one requires someone who actually knows the recipe to answer -- and that person is usually Somchai, who's also cooking.

NZ's food safety law requires businesses to know and disclose allergens when asked. Most small restaurants handle this verbally, with no documented system. The accuracy of the answer depends entirely on who's working that shift. Sen Vietnamese in Auckland openly notes on their website that staff must "advise which items cannot be made coeliac-safe due to having only one fryer." That's honest -- but it highlights how much of allergen management in NZ restaurants is ad hoc.

Why Existing Tools Don't Solve This

Your printed menu might have a "contains nuts" symbol next to a few dishes. But it doesn't cover cross-contamination, hidden ingredients like shrimp paste in curry paste, or the fact that your single fryer means nothing is truly gluten-free.

Generic allergen management software exists for large food manufacturers. It's not designed for a 40-seat Thai restaurant. And your POS doesn't track ingredients -- it tracks sales.

NZ's gluten-free, vegan, and dairy-free culture is far more pronounced than many other markets. Customers expect detailed allergen information, and they expect it fast. "I'll go check with the chef" is not a competitive answer when the restaurant next door has it on a QR code.

How AI Solves This

Somchai's OpenClaw AI assistant has every dish catalogued with its full ingredient list -- including the hidden ones. Customers access it through a QR code on each table, or through the restaurant's website and WhatsApp.

A customer scans the QR code and selects their allergies:

Customer selects: Peanuts, Shellfish

AI: "Here are the dishes on our menu that are safe for you (no peanuts, no shellfish):

Starters:

  • Spring rolls (vegetable) -- rice paper, glass noodles, vegetables. Served with sweet chilli (no fish sauce)
  • Corn fritters -- corn, curry paste (peanut-free, shrimp-free version available)

Mains:

  • Massaman curry (chicken) -- uses our house curry paste, peanut-free. Note: traditional massaman contains peanuts, but we make ours without for this reason
  • Basil stir-fry (tofu or chicken) -- soy sauce based, no fish sauce, no shrimp paste
  • Fried rice (chicken or vegetable) -- soy sauce based

Not safe for you:

  • Pad thai -- contains crushed peanuts
  • Green curry -- curry paste contains shrimp paste
  • Tom yum soup -- contains shrimp/fish sauce
  • Satay -- contains peanut sauce

Cross-contamination note: Our kitchen uses a shared fryer for spring rolls and battered items. If you have a severe allergy, please let your server know and we can prepare items using a separate pan instead."

A staff member can also query the AI internally:

Staff (internal chat): "Table 4 asks if the larb can be made without fish sauce"

AI: "Larb normally uses fish sauce as the primary seasoning. We can substitute with soy sauce and lime juice -- the flavour will be different but it works. This makes it shellfish-free but NOT soy-free. Confirm with the customer and let the kitchen know to use the substitute dressing."

The AI doesn't just list allergens -- it understands the recipes well enough to suggest modifications and flag cross-contamination risks.

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 complete ingredient database for every dish, including sub-ingredients (e.g., what's in your curry paste, not just "curry paste")
  • Creating a QR code system that links each table to the AI allergen checker on your website
  • Setting up an internal staff channel so kitchen and floor staff can query allergen information instantly
  • Connecting the AI to WhatsApp so customers can check allergens before they even arrive
  • Building the knowledge base from a detailed walkthrough of your recipes with the head chef

Here's our process:

  1. We map your full menu -- We sit down with you (or your head chef) and document every dish, every ingredient, every sub-ingredient, and every cross-contamination risk. This is the foundation.
  2. We build the connections -- Our developers write a custom program (an API connector) that powers the QR code system, the customer-facing allergen filter, and the internal staff query tool. No manual data entry, no guesswork.
  3. We test end-to-end -- Every allergen scenario gets tested against your actual recipes before going live. We verify the AI's answers against what the chef confirms.
  4. We maintain it -- When you change a recipe, add a dish, or switch a supplier (which may change ingredients), we update the database.

You don't need to be technical. We handle all the development -- you tell us the recipes, and we build the system.

The Result

  • Instant allergen answers -- customers get accurate information in seconds, not minutes
  • Staff confidence -- no more guessing or running to the kitchen mid-service
  • Reduced risk -- every allergen answer is consistent, regardless of who's working
  • Cross-contamination transparency -- shared fryer, shared wok, and prep surface risks are flagged automatically
  • More covers from allergy-conscious diners -- customers with dietary needs actively seek out restaurants that handle allergens well

What AI Can't Do Here

  • AI can't guarantee zero cross-contamination -- that's a kitchen operations issue, not an information issue
  • AI won't replace the need for staff to confirm severe allergies face-to-face -- for anaphylaxis-level allergies, a human conversation is still essential
  • AI accuracy depends on your recipe database being correct -- if you change a recipe and don't update the system, the AI gives wrong answers
  • AI can't account for supplier ingredient changes -- if your curry paste supplier changes their formula, someone needs to update the database

Who This Is For

  • Thai, Vietnamese, and Asian restaurants where hidden allergens (fish sauce, shrimp paste, peanuts) are common
  • Restaurants that get frequent allergen questions and rely on staff memory to answer them
  • Any restaurant that's had a near-miss with an allergic reaction
  • Businesses in areas with a strong GF/vegan/DF customer base (common across NZ)

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

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.

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

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