Fixed quote after a free call

Restaurant AI phone answering that frees the host stand during service

We build an AI assistant for your phone line, website chat or WhatsApp that answers the routine questions, such as hours, parking, dress code, corkage, high chairs and large-party policy, from your own approved answers. It sends guests to your reservation page or takes a booking request, says it is automated, and hands allergen, complaint and event questions to a person. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What a restaurant AI phone system should and should not answer

The phone rings hardest at 7pm on a Saturday, exactly when the host is seating a full room. Most calls are the same handful of questions, and each one pulls someone away from guests who are standing at the door.

An assistant can take that load only if it stays narrow. It must answer from the venue's own wording, never guess whether a dish is safe for an allergy, and pass complaints, events and anything unusual to a person with the details already written down.

What we build

What our restaurant AI receptionist includes

Approved answer library

Hours, location, parking, menus, dress code, corkage, dogs, accessibility and large-party rules, written and approved by the manager.

Phone, chat or WhatsApp

A voice line in front of your number, a web chat widget, a WhatsApp number, or any mix of the three.

Booking requests

Sends guests to your reservation page, or collects date, time, party size and name as a request for the host.

Allergen hand-off

Allergen and dietary questions are never answered by the assistant; they go to a trained person with the reservation details attached.

Clear AI disclosure

The assistant says it is automated at the start and offers a person, or a call-back, at any time.

Transcript review

A simple view of conversations and a weekly list of questions it could not answer, so the library grows.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Guest calls or chats

    A guest rings the venue or opens chat and hears that the assistant is automated.

  2. 02 Automated

    Routine answer

    Questions covered by the library get a short answer and, by text or chat, a link.

  3. 03 Automated

    Booking request

    The guest is sent to the reservation page or a request is captured for the host.

  4. 04 Team review

    Host follows up

    The host confirms requests and calls back guests who asked for a person.

  5. 05 Manager or chef decides

    Allergens and complaints

    Allergen answers, complaints and exceptions are handled by the chef or manager.

How it behaves

How the restaurant AI chatbot behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the guest sees

  • A clear note that they are talking to an automated assistant
  • Short answers from the venue's own wording
  • A reservation link or a booking request
  • A person for allergens, complaints and events

What the team sees

  • Booking requests and call-backs in one list
  • Allergen questions flagged with the reservation attached
  • A weekly list of questions the assistant could not answer

What the automation does

  • Matches questions to the approved library
  • Refuses allergen and complaint answers and hands over
  • Logs every conversation for review

Edge cases and fallbacks

Question not in the library
The assistant says it does not know, offers a call-back and adds the question to the review list.
Guest asks about an allergy
No answer on safety; the question and reservation go to a trained person.
Guest is angry about a past visit
Apologises, takes details and passes it to the manager straight away.
AI or telephony outage
Calls ring through to the venue as before and chat shows a contact form.
Large party or buyout request
Captured with date and numbers and sent to the events coordinator.

Architecture

An AI phone and chat assistant for a restaurant at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Guest Phone, chat, WA Assistant service n8n or Laravel Language model Claude, Gemini, GPT Approved answers Venue-written Booking request Or booking page Host or manager Allergens, events Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A guest calls, chats on the website or messages on WhatsApp and is told the assistant is automated.
  2. 2 The service retrieves the matching approved answers and passes them, with fixed rules, to the model.
  3. 3 Routine questions are answered; booking requests go to the reservation page or the host's list.
  4. 4 Allergen questions, complaints and events go straight to a person, and every conversation is logged.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI phone answering & restaurant chatbot project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Listen to real calls and messages, agree what the assistant may and may not answer.

  2. 02

    Answer library

    About 1 week

    Write and approve answers with the manager, including allergen and complaint hand-off wording.

  3. 03

    Build

    About 2 weeks

    Voice line or chat, retrieval, booking request, hand-off alerts, logging and admin view.

  4. 04

    Test

    1 to 2 weeks

    A test set of real questions plus tricky allergen and complaint prompts; the manager signs off.

  5. 05

    Launch

    2 to 3 days

    Start with overflow calls or after-hours chat, then widen.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly library updates for menus and seasons.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models n8n AI Agent node or Laravel Twilio Voice and Messaging WhatsApp Business Platform Your reservation page (OpenTable, SevenRooms, Resy or similar) Slack or email for staff alerts

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real calls reviewed, answers written and approved.

    $500 – $1,200

  • Build

    Assistant service, voice or chat, retrieval, hand-off and admin view.

    $1,200 – $4,000

  • Integrations

    Reservation page, telephony, WhatsApp and staff alerts.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and allergen prompts tested before launch.

    $300 – $900

  • Launch and training

    Soft launch, transcript review and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A voice line costs more to build and run than web chat. Model usage, telephony and WhatsApp fees are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; short answers at restaurant volumes are usually a small monthly amount.
  • Telephony and messaging: Twilio voice and SMS at published rates (US SMS about $0.0083 per segment plus carrier fees); WhatsApp at Meta's own rates.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell guests they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are dealing with an AI system, from 2 August 2026. We add the disclosure everywhere.

Source: artificialintelligenceact.eu

US: nine major food allergens

The FDA recognises nine major allergens, with sesame added from January 1, 2023. The assistant never says a dish is free from any of them; a person answers.

Source: www.fda.gov

EU and UK: allergen information for loose food

Regulation 1169/2011 requires allergen information for non-prepacked food too, and lets countries set how it is given. The assistant points guests to staff, who give it.

Source: www.legislation.gov.uk

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

Restaurant AI phone answering questions questions, answered.

It can send guests to your reservation page or collect a booking request for the host. Writing straight into the book depends on your platform and the access it grants, so we start with requests and confirm the route per project.

No. It tells the guest a trained member of staff will confirm, takes their details and the reservation, and alerts the team. A confident wrong answer about an allergen is too serious a risk to automate.

It can send guests to your online ordering page by text. Taking full orders by voice into the POS needs a POS integration, which we scope separately and only with POS systems that allow it.

Yes. It says so at the start and offers a person or a call-back at any time. In the EU this is required under the AI Act from 2 August 2026, and we do it everywhere.

Yes, and in much of Europe, Latin America and Asia guests prefer it. We use the official WhatsApp Business Platform and approved message templates.

We log every conversation and send a weekly list of unanswered questions. Watch calls handled without staff, booking requests captured and what guests ask that is missing from the library.

Free 20-minute call

Want this for your restaurants & café?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call