All Case StudiesHospitality

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.

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

The Real Problem

Dave and Karen run a fish and chips shop on the Takapuna beachfront. They've been there 11 years. It's the kind of place with a queue out the door on a sunny Friday evening and regulars who've been coming since their kids were in primary school.

Friday night at 5:30pm is controlled chaos. Dave is running the fryer. Karen is wrapping orders, taking payments, and managing the counter queue. There are two of them. That's it.

The phone rings.

Karen is mid-transaction. Dave has both hands in batter. The phone rings out. It rings again. Someone in the queue picks up -- "Hello? ... Yeah, they're busy, call back later." The caller hangs up.

Dave and Karen estimate they miss 10-15 phone calls every Friday evening between 5:30 and 8pm. At an average order of $25-30, that's $250-400 in lost revenue. Every single Friday.

Phone ordering is still how a huge number of Kiwi fish and chips shops operate, especially outside central Auckland. Customers call ahead, place their order, and pick up 15 minutes later. It's been the system for decades. But it only works when someone can answer the phone -- and during peak, nobody can.

This isn't a staffing choice. It's economics. Fish and chips shops run on tight margins. The Spinoff reported frying oil costs up 8.2%, vegetables up 9.2%, and fish up 5% year-on-year. 82% of Auckland hospitality operators reported being understaffed in recent surveys. Hiring a third person for Friday nights just to answer phones doesn't make financial sense.

Why Existing Tools Don't Solve This

There's no NZ-specific AI phone ordering product for takeaways. In the UK, a company called ServeMate built an AI phone assistant called "Sophie" for chip shops -- it's now in over 100 UK takeaways. In Australia, DinelineAI serves a similar market. In the US, Loman AI and Kea handle restaurant phone orders. But none of these serve New Zealand.

Your EFTPOS terminal doesn't take phone orders. Your POS tracks what you sell, not what you missed. Online ordering platforms like Menulog or Uber Eats take a 30% cut -- and for a fish and chips shop doing $25 average orders, that margin hit is devastating.

Some shops put up a sign: "No phone orders during busy periods." That's honest, but it sends customers elsewhere.

How AI Solves This

Dave and Karen's OpenClaw AI assistant answers every phone call -- simultaneously. When a customer calls, the AI picks up instantly:

AI: "G'day, you've reached [Shop Name] in Takapuna! I can take your order right now. What can I get you?"

Customer: "Yeah, can I get two fish, large chips, one hot dog, and a blue Powerade?"

AI: "No worries. So that's:

  • 2x battered fish -- $8.50 each
  • 1x large chips -- $7.00
  • 1x hot dog -- $5.50
  • 1x blue Powerade -- $4.50

Total comes to $34.00. Pickup in about 15 minutes -- that'll be around 6:05pm. Name for the order?"

Customer: "Mike."

AI: "Sweet as, Mike. Your order's in. See you at 6:05!"

The order goes straight to the kitchen -- printed on the ticket printer or displayed on a screen. Dave sees "Mike -- 2 fish, large chips, hot dog, Powerade -- 6:05pm" and drops it in the queue. No phone call, no interruption, no scribbled note.

Meanwhile, another customer calls at the exact same time:

AI: "G'day, you've reached [Shop Name]! What can I get you tonight?"

Customer: "What fish have you got today?"

AI: "Tonight we've got snapper and tarakihi. Snapper's $9.50 a piece, tarakihi's $8.50. Both battered fresh. The snapper's been really popular tonight -- we've been going through it fast."

Customer: "Two snapper and a scoop of chips."

AI: "Two snapper, scoop of chips. That's $24.00. Ready in about 12 minutes. Name?"

The AI handles unlimited concurrent calls. Five phones ringing at once? Five orders taken simultaneously. No hold music, no busy signal, no missed calls.

What the AI Knows

The AI's knowledge base includes:

  • Full menu with current prices and tonight's available fish
  • Pickup time estimates based on current order volume
  • Common questions -- "Do you have gluten-free options?" "Is the fish crumbed or battered?" "Do you do calamari?"
  • Specials and combos -- "Friday family deal: 4 fish, 2 large chips, 4 drinks for $55"

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 your phone line so it answers calls automatically during peak hours (or all the time, if you prefer)
  • Integrating with your kitchen display or ticket printer so orders appear instantly without manual entry
  • Building your menu into the AI's knowledge base, including daily fish availability, specials, and combo deals
  • Setting up pickup time estimation based on your typical prep times and current order queue
  • Configuring the AI's voice and personality to match your shop's style -- friendly, casual, Kiwi

Here's our process:

  1. We map your current workflow -- We figure out how orders currently come in, what your peak times look like, and how your kitchen processes tickets.
  2. We build the connections -- Our developers write a custom program (an API connector) that links the AI phone system to your kitchen workflow. Orders flow from phone call to ticket printer with zero manual steps.
  3. We test end-to-end -- We run test orders through the system during a quiet period to make sure every order type works -- simple orders, special requests, questions about the menu.
  4. We maintain it -- When you change your menu, adjust prices, or add a seasonal special, we update the system.

You don't need to be technical. We handle all the development -- you tell us your menu and how your kitchen works, and we build the system around that.

The Result

  • Zero missed calls -- every phone order is captured, even when five people call at once
  • $250-400 recovered per Friday -- orders that used to be lost now come through
  • Staff stay on the fryer -- Dave and Karen keep doing what they do best instead of running to the phone
  • Faster order turnaround -- AI-taken orders are instantly in the kitchen queue, no handwriting to decipher
  • After-hours pre-ordering -- customers can call at 3pm and place their order for 6pm pickup

What AI Can't Do Here

  • AI won't handle complex custom requests -- "can you do the fish but only lightly battered and cooked at a lower temperature" needs a human
  • AI can't manage your food prep -- it estimates pickup times, but you need to adjust if you're running behind
  • AI won't resolve disputes -- if someone says their order was wrong, that's a human conversation
  • AI needs accurate menu data -- if you run out of snapper and don't update the system, the AI will keep selling it

Who This Is For

  • Fish and chips shops where phone orders are a major part of the business
  • Two-person operations where nobody can answer the phone during rush
  • Any takeaway losing orders because the phone rings out during peak times
  • Shops that have considered online ordering platforms but can't afford the 30% commission

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

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

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