All Case StudiesHospitality

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 min readUpdated 2026-04-03Based on 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)

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

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.

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

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