Case Study

Case Study: Restaurant Guest CRM & Booking Automation

We built a connected set of automations for an independent full-service restaurant with a private dining room: one guest CRM, an AI assistant for routine calls and chats, no-show reminders with a waitlist, private event booking from enquiry to final numbers, and review requests with reply drafts. The host stand now answers fewer routine calls during service, and the manager and chef only see what needs their decision.

Venue type
Independent full-service restaurant with a bar and private dining room
Team involved
Owner, general manager, events coordinator, head chef, hosts
Systems connected
Reservation platform, POS, events tool, email marketing, Google Business Profile, Twilio, n8n
Delivery
Scrum, 1-week sprints, about 8 weeks to full launch

The challenge

Where the practice started

The phone rang most during dinner service, and the host was answering the same questions about parking and corkage while guests waited at the door.

Guest details sat in the reservation platform, the POS and an old mailing list. Nobody could say who the regulars were or who had not been back in months.

Large parties ignored reminders and some never arrived, while the waitlist was kept on paper and rarely used when a table opened.

Private dining enquiries waited days for a proposal because the coordinator also ran the floor, and reviews were answered in bursts, late at night, with no agreed tone.

Goals

What the project had to change

  • Routine calls and chats are answered without pulling the host off the floor, and allergen questions always reach a person.
  • Every guest has one profile, and marketing only reaches guests who opted in.
  • Unconfirmed large parties get a call and cancelled tables reach the waitlist quickly.
  • Every private dining enquiry gets a proposal draft the same day.
  • Every guest is asked for a review the same way, and replies follow one calm tone.

What we built

What we built, as one connected system.

01

Guest CRM

We merged reservations, POS customer records and sign-ups into one guest profile with consent attached, nightly segments for regulars, lapsed guests and private diners, and a weekly report by campaign.

Service details
02

AI phone and chat assistant

An assistant on the overflow line and website chat answers routine questions from the manager's approved library, sends guests to the reservation page and hands allergen questions, complaints and events to a person.

Service details
03

No-show reminders and waitlist

Confirm-or-cancel messages at the time the manager chose, a large-party call list for the host, automatic waitlist offers and a pre-service list of confirmed covers.

Service details
04

Private event booking

Enquiries from the website and email land in the events tool in one format, the room is checked, a proposal is drafted from approved packages, and deposit and final-number reminders run on schedule.

Service details
05

Review requests and replies

One request after each visit to guests who agreed to contact, same-day alerts for new reviews and reply drafts the manager edits and posts.

Service details

Architecture

How the restaurant's workflows connect

Phone and chat Guest questions Reservations Bookings, waitlist Web and events Enquiries, sign-ups n8n Five workflows AI assistant Answers, drafts Guest CRM Profiles, consent Texts and emails Twilio, email Hosts, coordinator Lists, proposals Manager and chef Allergens, offers Log and reports Weekly summary
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 Calls and chats, reservations and the waitlist, and web enquiries and sign-ups feed one n8n instance.
  2. 2 Five workflows update the guest CRM, send messages and use an AI step to answer routine questions and draft proposals and replies.
  3. 3 Hosts and the coordinator work one set of lists; the manager and chef handle allergens, offers and exceptions.
  4. 4 Every step is logged, and a weekly summary shows the measures the venue agreed to track.

How it behaves

How the system behaves day to day

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

What guests see

  • A quick answer to routine questions by phone or chat
  • One confirm-or-cancel message before their booking
  • A same-day reply and a clear proposal for private dining
  • One polite review request after their visit

What the team sees

  • A call list, a pre-service list and an events pipeline
  • Allergen questions with the reservation attached
  • Draft review replies to approve
  • A weekly guest and booking report

What the automation does

  • Answers, confirms, reminds and chases on schedule
  • Applies consent and opt-outs across every workflow
  • Logs every step and alerts the manager if anything fails

Edge cases and fallbacks

A guest asks about a severe allergy
The assistant takes details and alerts a trained person; it never says a dish is safe.
A guest opts out in one workflow
One shared opt-out list stops marketing from every workflow.
The reservation platform API is unavailable
The platform's own reminders keep running and our updates retry later.
An event enquiry clashes with a buyout
The coordinator sees the clash and offers alternatives personally.
Twilio or n8n has an outage
Calls ring through to the venue as before and the manager gets an alert.

Integrations

What we connected

All integrations

SevenRooms

Reservations and guest CRM

Reservations, guest profiles and tags for the CRM, reminders and waitlist.

SevenRooms advertises an API and 100+ integrations, including Toast, Square, Twilio, Mailchimp and Tripleseat; access confirmed per project.

Toast

POS and online ordering

Orders, checks and menus for the CRM, review timing and the website.

Toast APIs (orders, menus, restaurants) under partner, custom or standard API access.

Tripleseat

Private events

Leads, events and contacts for private dining and buyouts.

Tripleseat API: public-key lead creation and OAuth 2.0 for leads, events, bookings and contacts.

Klaviyo

Email and SMS marketing

Segments, lifecycle emails and consent-based campaigns.

Klaviyo's API, and its OpenTable app, which syncs reservation events and POS orders where the POS is connected to OpenTable.

Google Business Profile

Reviews and local search

Booking and ordering links, review requests and new-review alerts.

Google Business Profile settings and APIs.

Twilio

SMS and voice

Confirmations, waitlist offers, AI phone line and opt-out handling.

Twilio Programmable Messaging and Voice APIs.

Slack and Microsoft Teams

Staff alerts

Allergen questions, new reviews, event enquiries and failure alerts.

Incoming webhooks and APIs.

n8n

Automation platform

Runs every workflow, self-hosted or on n8n Cloud.

Your own n8n instance; we hand over every workflow.

How we delivered it

Week by week, one workflow at a time.

Each workflow went live on its own after a shadow run and a sprint demo, so the team got used to one change before the next.

Delivery timeline

Typical time to launch: about 8 weeks, then support

  1. 01

    Discovery

    Week 1

    We shadowed two dinner services, listened to calls, mapped the reservation, event and review steps and agreed allergen hand-off wording.

  2. 02

    Design and access

    Week 2

    Approved answer library, message templates, consent rules, platform access requests, Twilio number and A2P 10DLC registration.

  3. 03

    Sprint 1: no-shows

    Week 3

    Built and shadow-ran confirmations, the large-party call list and waitlist offers against a test phone; demo and sign-off.

  4. 04

    Sprint 2: guest CRM

    Week 4

    No-show reminders went live. Merged guest records, built segments and the weekly report.

  5. 05

    Sprint 3: events

    Week 5

    The CRM went live. Built event capture, room check, proposal drafts and reminders.

  6. 06

    Sprint 4: AI assistant

    Week 6

    Event booking went live. Built the phone and chat assistant and tested it against real and allergen questions.

  7. 07

    Sprint 5: reviews

    Week 7

    The assistant went live on after-hours chat. Built review requests, alerts and reply drafts.

  8. 08

    UAT and handover

    Week 8

    The team ran acceptance tests on every workflow, the assistant moved to the overflow line, and we handed over the run book.

  9. 09

    Support

    Ongoing

    Weekly check-ins during stabilisation, then monthly care for menus, seasons and packages.

Who does what

What the team does, and what automation does.

Automation does

  • Answers routine calls and chats from the approved library
  • Merges guest records and keeps consent with each profile
  • Sends confirmations and offers released tables to the waitlist
  • Captures event enquiries and drafts proposals
  • Detects new reviews and drafts replies

The team does

  • Hosts call unconfirmed large parties and confirm booking requests
  • The coordinator edits, prices and sends every proposal
  • Staff take allergen questions to the kitchen and reply
  • The manager approves campaigns and every review reply

Manager or chef decides

  • The head chef confirms every allergen answer and event dietary list
  • The manager sets no-show policy, offers and minimum spends
  • The owner approves pricing and any comps or refunds

Compliance handled

Privacy, consent and safety, built in.

Allergen answers come from people

The assistant and workflows never say a dish is free from an allergen; a trained person confirms every answer.

Source: www.fda.gov

Texting rules in the US

Confirmations stay transactional; promotions need prior express written consent and live in a separate flow.

Source: www.law.cornell.edu

A2P 10DLC registration

The venue's texting number was registered for A2P 10DLC before launch.

Source: www.twilio.com

AI disclosure

The assistant says it is automated at the start of every call and chat, in line with Article 50 of the EU AI Act.

Source: artificialintelligenceact.eu

No review gating

Every eligible guest is asked the same way, with no incentives.

Source: support.google.com

Card data stays with providers

Deposits are taken on the reservation and payment providers' hosted pages, so card numbers never pass through our workflows.

Source: www.pcisecuritystandards.org

Outcomes

What changed for the practice

  • Routine calls during service are now answered without pulling the host away from the door.
  • Every guest has one profile, and marketing reaches only guests who opted in.
  • Unconfirmed large parties get a call before service, and cancelled tables are offered to the waitlist straight away.
  • Private dining enquiries get a proposal draft the same day.
  • Every guest is asked for a review the same way, and replies follow one calm tone.
  • Allergen questions always reach a trained person with the reservation attached.

What we track

The measures the practice watches.

Calls handled

Share of calls and chats answered without staff, and booking requests captured.

No-shows

No-shows and late cancellations by day and party size, and tables re-filled from the waitlist.

Returning guests

Share of covers from returning guests and lapsed guests won back after a message.

Event pipeline

Time to first proposal, proposals sent and deposits paid each month.

Reviews

Requests sent, reviews received and average time to an approved reply.

Cost estimate

What a project like this costs

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

    Service shadowing, data flows, wording and the backlog for all five workflows.

    $1,000 – $2,000

  • Guest CRM module

    Record merging, segments, consent and the weekly report.

    $700 – $1,600

  • AI assistant module

    Answer library, voice and chat, hand-off and logging.

    $1,300 – $3,200

  • No-show module

    Confirmations, call list, waitlist and pre-service list.

    $600 – $1,500

  • Private events module

    Capture, room check, proposal drafts and reminders.

    $700 – $1,700

  • Reviews module

    Requests, alerts and reply drafts.

    $500 – $1,200

  • Integrations

    Reservation platform, POS, events tool, email and Twilio.

    $300 – $800

  • Testing, UAT and launch

    QA, acceptance testing, launch and training.

    $400 – $1,500

  • Total project estimate

    $5,500 – $13,500

Optional monthly care after launch is quoted with your proposal. Typical range for a project of this scope: four workflows at our fixed per-workflow range plus an AI assistant. Every venue gets its own fixed quote after a free call.

Monthly running costs you pay directly

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

  • Twilio SMS (US): About $0.0083 per message segment plus carrier fees, and about $1.15 a month per local number (Twilio's published US pricing), plus A2P 10DLC registration fees.
  • n8n: Free self-hosted Community edition, or n8n Cloud from about €20 a month (Starter) or €50 (Pro), billed annually.
  • Reservation, events and email tools: Each vendor's own plan.
  • AI and telephony usage: Pay-per-use model and voice fees, usually small at a single venue.

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

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.

Free 20-minute call

Want this built 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