Back to AI Agent & Chatbot

Restaurants & cafés · 08 / 12

Ordering and table booking agent

At peak hours customers book a table or order takeaway on LINE themselves, against real seating and the real menu, so nobody puts down a plate to answer the phone.

In a busy restaurant kitchen a chef cooks at the stove while a server reads an order on a tablet, full tables behind them. Restaurants & cafés
“At peak hours nobody can answer the phone for reservations, and takeaway orders on LINE go unanswered.”

The problem

From six to eight in the evening everyone in the restaurant has a plate in their hands. The phone rings for reservations and nobody can get to it, while a dozen takeaway orders sit unopened on LINE OA. By the time someone replies at nine, the customer has ordered from somewhere else.

Phone bookings go into a notebook. Some days they are written twice, some days not at all, and a customer arrives to find no table. Orders taken in chat need someone to walk to the kitchen and key them into the POS a second time.

How we solve it

We connect the agent to the restaurant’s POS and reservation system. When a customer messages on LINE OA asking for a table for four at seven, it checks the seats free in that sitting, books it on the spot and sends a reminder before the time. If the customer cancels, the table goes back to the pool for the next person with nobody correcting a notebook.

Takeaway orders are taken from the current menu and prices in the POS. If a dish is sold out, the agent says so and suggests something similar. A confirmed order goes into the POS and the kitchen display by itself, and the customer gets a pickup time and a payment link. Questions about allergens, vegetarian dishes or parking are answered from the information the restaurant provides.

Large group bookings, private events and complaints about the food go to the restaurant manager at once, and refunds or compensation are always a person’s call.

How it runs

Work comes in from
  • LINE OA and Messenger
  • Chat from Google Business Profile
  • Menu and stock from the POS
  • Free seats from the reservation system
What the AI does
  1. Check free seats and book the table
  2. Take the order from the current menu
  3. Answer menu and allergen questions
  4. Pass events and complaints to the manager
Where it lands
  • Reservation in the system with a reminder
  • Order in the POS and kitchen display
  • Customer gets pickup time and payment link
  • Dashboard of chat bookings and orders

Before and after

Before
After
At peak hours the reservation phone goes unanswered
Customers book on LINE themselves against the seats actually free
Takeaway orders sit in LINE until the customer orders elsewhere
Takeaway orders reach the POS and kitchen within the first minute
Phone bookings go in a notebook, sometimes twice, sometimes lost
Every booking lives in one system, and a cancelled table frees itself

What you get

  1. 01

    An agent that takes reservations against the seats actually free in each sitting, reminds before the time and releases the table on cancellation

  2. 02

    Takeaway orders taken from the current menu and prices, sent to the POS and kitchen, with a pickup time and payment link

  3. 03

    Questions about the menu, allergens, vegetarian and halal options, parking and opening hours answered from the restaurant’s own information

  4. 04

    Sold-out items hidden automatically from the POS, with a similar dish suggested instead

  5. 05

    A message after the meal asking for a Google review, and promotions sent to customers who have ordered before

Who gets what

Business owner

Full bookings and orders through the whole peak without extra staff, and a view of which dishes sell through chat.

IT director

Connected to the POS the restaurant already uses through the vendor’s API, with the menu and prices read from one place so there is no second menu to maintain, and payment through the provider the restaurant already has.

The team using it every day

Floor staff stop running to the phone mid-service and look after the customers at the tables.

Who this fits

Restaurants & cafésMulti-branch restaurantsBuffet & grill restaurantsBakeries & pre-order kitchensHotel restaurants

Connects with what you already run

POSLINE OAReservation systemOmiseGoogle Business ProfileGrabFood

Development process

  1. 1

    Discover

    Requirements, users and success metrics, with scope and price fixed before we start.

  2. 2

    Design

    UX and system architecture; the prototype is approved before anything is built.

  3. 3

    Build

    AI-accelerated sprints with a demo every week, reviewed by senior engineers.

  4. 4

    Test

    QA, security and performance verified against the agreed scope.

  5. 5

    Launch & care

    Production deploy, team training, and a monthly care plan.

Turn your business problem into a system that works for you

Tell us today — get an executive-ready proposal with the plan and budget.

Talk to an engineer about this