All Case StudiesHospitality

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.

5 min readUpdated 2026-03-15Based on Claude Sonnet 4 / GPT-4o

The Real Problem

It's 7:15pm on a Friday. Your restaurant is full. Three tables are waiting for mains, a couple has just arrived for their 7:30 booking, and the bar is two-deep with walk-ins hoping for a seat.

The phone rings.

Nobody answers it. Your front-of-house manager is seating the couple. Your bartender is pouring drinks. You're expediting in the kitchen. The phone rings out.

That call was a table of six wanting to book for next Saturday — a $600+ cover. They call the restaurant down the road instead.

This scenario plays out every night in NZ hospitality. Many restaurants still rely on phone calls for bookings — OpenTable has minimal traction in NZ, and a large number of restaurants don't use dedicated booking platforms. From Reddit: "Most NZ restaurants will let you book online otherwise you can always give them a call."

The problem is that calls peak during service — exactly when nobody can answer. And unlike a retail shop, you can't just let it ring. Every unanswered call during service is potentially a lost booking, a catering enquiry, or a large party celebration.

Why Existing Tools Don't Solve This

Dedicated AI phone answering for restaurants exists in the US — Loman AI, Slang AI, RestoHost, Newo AI. But none of them serve the NZ market. They don't understand NZ English, don't integrate with NZ-specific booking systems like First Table or ResDiary, and are priced for the US market.

Your POS (Lightspeed, Square) doesn't answer phones. Your booking system (if you have one) takes online bookings but doesn't handle phone enquiries. Your voicemail message says "leave a message and we'll call you back" — but you never do, because by the time service ends, it's 11pm.

How AI Solves This

Your OpenClaw AI assistant is connected to your business WhatsApp. When a call goes unanswered, the caller immediately receives a WhatsApp message:

Hi! Thanks for calling [Restaurant Name]. We're in the middle of service right now, but I can help you with:

📅 Make a booking — just tell me the date, time, and party size 📋 Menu questions — dietary requirements, specials, etc. 🕐 Opening hours — we're open Tue-Sat, 5:30pm-late

Or I can have someone call you back after service. What can I help with?

The customer replies:

"Can I book a table for 6 on Saturday night? Around 7:30. Two of us are vegetarian."

The AI responds:

I've got availability for 6 at 7:30pm this Saturday. I'll reserve that for you now! A couple of things:

  • We have several vegetarian options on our current menu, including our mushroom risotto and the roasted cauliflower — both very popular.
  • For a group of 6, I'd suggest our long table by the window if you'd like a bit more space.
  • Can I take a name and contact number for the booking?

The customer provides their details. The AI:

  1. Confirms the booking via WhatsApp
  2. Sends you a notification: "New booking: 6 pax, Sat 7:30pm, [Name], 2 vegetarian — window table requested"
  3. Logs it in your workspace for transfer to your booking system

You see the notification when you get a quiet moment — the booking is already handled.

Common Enquiries the AI Handles

The AI's knowledge base includes your:

  • Menu (current dishes, dietary options, allergen info)
  • Opening hours and public holiday closures
  • Booking availability (times and party sizes you've configured)
  • FAQ answers (parking, BYO policy, kids' menu, dress code, accessibility)
  • Event and function enquiry handling (captures details, sends to you for follow-up)

For questions it can't answer — pricing for private functions, specific ingredient sourcing, special requests — it captures the enquiry and flags it for your personal follow-up.

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 to WhatsApp and Facebook Messenger so customers can reach you on the channels they already use
  • Syncing with your calendar so AI-booked appointments appear in your real schedule
  • Setting up email notifications and automated follow-up sequences
  • Building your knowledge base from an initial interview and keeping it updated as your business evolves

Here's our process:

  1. We map your current workflow — We sit down with you and figure out what tools you're using and how enquiries currently flow through your business.
  2. We build the connections — Our developers write a custom program (an API connector) that lets the AI talk to your systems. No manual data entry, no copy-pasting between apps.
  3. We test end-to-end — Every workflow gets tested with real scenarios before going live. Nothing launches until it works reliably.
  4. We maintain it — When your business changes, we update the integration 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

  • Zero missed booking opportunities — every call gets an instant, helpful response
  • Staff stay on the floor — no more pulling FOH away from tables to answer phones
  • Bookings confirmed in real-time — customers don't have to wait until tomorrow
  • Dietary needs captured upfront — kitchen gets advance notice of vegetarian/GF/allergy requirements
  • After-hours coverage — the AI handles enquiries at 2am from people planning ahead

What AI Can't Do Here

  • AI won't take orders for delivery or takeaway (that's your POS/delivery platform's job)
  • AI won't handle complaints during service — those need a human touch
  • AI won't override your booking capacity — it works within the availability you set
  • AI can't assess the caller's tone — urgent or emotional callers should speak to a person

Who This Is For

  • Restaurants that still rely on phone bookings (common in NZ)
  • Busy venues where phones ring unanswered during peak service
  • Owner-operators who answer the phone themselves while cooking
  • Any restaurant that doesn't have a dedicated receptionist/host

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

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

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