Case Study

Case Study: Boutique Hotel Guest CRM & Messaging

We built a connected set of automations for an independent boutique hotel: a guest database and CRM fed by the PMS, an AI assistant for guest messages, pre-arrival emails with online check-in and extras, guest requests turned into housekeeping tasks, and review replies the manager approves. The front desk now works from one arrivals list and one request log, and the manager only sees what needs a decision.

Property type
Independent boutique hotel with a small restaurant
Team involved
Owner, general manager, front desk, head housekeeper, maintenance
Systems connected
Cloud PMS, booking engine, email marketing, WhatsApp, Google Business Profile, n8n
Delivery
Scrum, 1-week sprints, about 8 weeks to full launch

The challenge

Where the practice started

Guest messages arrived through the website, email, WhatsApp and OTA inboxes, and the front desk answered the same questions about parking and check-in many times a day.

The PMS held years of stays, but duplicates and OTA alias emails meant nobody could say who the repeat guests were, and past guests never heard from the hotel directly.

Arrival details were collected at the desk, so check-in queues built up on busy afternoons, and extras were rarely offered.

Requests were passed on by sticky note and WhatsApp, some were lost between shifts, and reviews were answered in occasional late-night bursts.

Goals

What the project had to change

  • Routine guest questions are answered on every channel, and sensitive messages reach a person quickly.
  • Every guest has one clean profile, and marketing reaches only guests who opted in.
  • Arrival details and requests are in the PMS before the guest arrives.
  • Every request is logged, routed and closed, with the guest told when it is done.
  • Every review gets a calm reply approved by the manager.

What we built

What we built, as one connected system.

01

Guest database and CRM

We read stays from the PMS nightly, merged duplicate profiles, tagged repeat guests and occasions, kept consent with each record and set up a thank-you, an anniversary note and a seasonal invitation.

Service details
02

AI guest messaging

An assistant on website chat and WhatsApp answers routine questions from the manager's approved facts, logs requests against the booking and hands complaints, refunds and accessibility questions to the front desk.

Service details
03

Pre-arrival and online check-in

A pre-arrival email three days out with an online check-in form, extras at their total price and answers written to the reservation, plus a daily arrivals list.

Service details
04

Requests to housekeeping tasks

Every request from messages, the desk and the phone becomes a task on the team's chat app, with room status from the PMS, escalation timers and a guest update when done.

Service details
05

Review replies

Fair post-stay requests, new reviews gathered in one feed, and reply drafts the manager edits and posts.

Service details

Architecture

How the hotel's workflows connect

PMS Stays, arrivals Guest messages Chat, WhatsApp Review sites Google, OTAs n8n Five workflows AI assistant Answers, drafts Guest CRM Profiles, consent Task log Requests, rooms Front desk Arrivals, requests Manager Replies, exceptions Log and reports Monthly summary
  • Input
  • Logic and services
  • AI step
  • Data
  • People

How it flows

  1. 1 Stays and arrivals from the PMS, guest messages and new reviews feed one n8n instance.
  2. 2 Five workflows update the guest CRM and task log and use an AI step to answer questions and draft replies.
  3. 3 The front desk works one arrivals list and one request log; the manager approves replies and exceptions.
  4. 4 Every step is logged, and a monthly summary shows the measures the hotel 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

  • Quick answers on chat and WhatsApp, with a person when needed
  • A short pre-arrival email and online check-in
  • Requests acknowledged and closed with an update
  • One fair review request after checkout

What staff see

  • One arrivals list and one request log
  • Sensitive messages flagged with the booking attached
  • Draft review replies to approve
  • A monthly guest report

What the automation does

  • Answers, sends, logs and routes 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 reports a safety issue by message
The duty manager is alerted at once; no automated advice is given.
A guest requests an accessible room change
The front desk confirms and blocks the room; the assistant never promises it.
The PMS API is unavailable overnight
The CRM run and arrivals list retry later and never send from stale data.
A review names a staff member
The draft avoids repeating names and the manager handles follow-up.
WhatsApp or n8n has an outage
Web chat shows a contact form, staff use the radio for tasks and the manager gets an alert.

Integrations

What we connected

All integrations

Mews

PMS

Reservations and customers for the CRM, pre-arrival, requests and availability.

Mews Connector API (reservations, customers), server to server.

Cloudbeds

PMS and booking engine

Reservations, guests and rooms for the CRM, pre-arrival and requests, with booking webhooks.

Cloudbeds API and webhooks; API access depends on plan tier.

Google Business Profile

Reviews and local search

Review requests, new-review alerts and booking links.

Google Business Profile settings and APIs.

HubSpot

CRM

Guest contacts and group deals for smaller properties.

HubSpot's CRM REST API.

WhatsApp Business Platform

Messaging

AI assistant, requests and guest updates.

Meta's WhatsApp Business Platform with approved templates.

Slack and Microsoft Teams

Staff tasks and alerts

Housekeeping and maintenance tasks, escalations 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 the front desk and housekeeping, gathered real guest messages, mapped arrivals, requests and reviews, and agreed hand-off rules.

  2. 02

    Design and access

    Week 2

    PMS API access, approved answer library, email and form wording, consent rules, WhatsApp number and processor agreements.

  3. 03

    Sprint 1: pre-arrival

    Week 3

    Built and shadow-ran the pre-arrival email, online check-in form and arrivals list; demo and sign-off.

  4. 04

    Sprint 2: requests

    Week 4

    Pre-arrival went live. Built the request log, routing to the team chat and guest updates.

  5. 05

    Sprint 3: guest CRM

    Week 5

    The request log went live. Built PMS sync, duplicate merging, tags and emails.

  6. 06

    Sprint 4: AI messaging

    Week 6

    The CRM went live. Built the assistant for web chat and WhatsApp and tested it with real and tricky messages.

  7. 07

    Sprint 5: reviews

    Week 7

    The assistant went live overnight. Built post-stay requests, the review feed and reply drafts.

  8. 08

    UAT and handover

    Week 8

    The team ran acceptance tests on every workflow, the assistant went live around the clock, and we handed over the run book.

  9. 09

    Support

    Ongoing

    Weekly check-ins during stabilisation, then monthly care.

Who does what

What the team does, and what automation does.

Automation does

  • Answers routine guest questions from approved facts
  • Merges guest profiles and keeps consent with each record
  • Sends pre-arrival emails and writes answers to the PMS
  • Logs requests and routes them as tasks
  • Gathers reviews and drafts replies

The team does

  • The front desk confirms requests and special needs
  • Housekeeping and maintenance complete and close tasks
  • Staff confirm unclear profile merges
  • The front desk handles messages the assistant hands over

Manager or owner decides

  • The manager approves every review reply
  • The manager decides refunds, upgrades and compensation
  • The owner sets rates, packages and offers to past guests

Compliance handled

Privacy, consent and safety, built in.

Total prices for extras

Extras and packages show the total price including mandatory fees, in line with the FTC rule in effect from May 12, 2025.

Source: www.ftc.gov

Accessible rooms confirmed by staff

Accessible room requests are confirmed and blocked by staff, never promised by automation.

Source: www.law.cornell.edu

AI disclosure

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

Source: artificialintelligenceact.eu

Processor agreements

Every vendor that touches guest data is under a processor agreement before go-live.

Source: gdpr-info.eu

Marketing consent

Emails to past guests go only to those who opted in, with an easy way to refuse.

Source: www.legislation.gov.uk

No review gating

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

Source: support.google.com

Outcomes

What changed for the practice

  • Routine guest questions are answered on chat and WhatsApp at any hour, with a person a tap away.
  • Every guest has one clean profile, and past guests hear from the hotel directly when they opted in.
  • Most arrival details and requests are in the PMS before the guest walks in.
  • Every request is logged, routed and closed, and guests are told when it is done.
  • Every review gets a calm, approved reply.
  • The front desk works from one arrivals list and one request log instead of several inboxes.

What we track

The measures the practice watches.

Messages resolved

Share of guest messages answered without staff, and response time overnight.

Online check-in

Share of arrivals completing the form and extras accepted by type.

Request times

Time to complete requests by type and overdue tasks per week.

Repeat guests

Repeat guest share and direct bookings from returning guests.

Reviews

Reviews per month, reply rate and 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

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

    $1,000 – $2,000

  • Guest CRM module

    PMS sync, merging, tags, consent and emails.

    $700 – $1,600

  • AI messaging module

    Answer library, web chat and WhatsApp, hand-off and logging.

    $1,300 – $3,200

  • Pre-arrival module

    Email, online check-in, extras and arrivals list.

    $600 – $1,500

  • Requests module

    Request log, routing, escalation and guest updates.

    $700 – $1,700

  • Reviews module

    Requests, review feed and reply drafts.

    $500 – $1,200

  • Integrations

    PMS, WhatsApp, team chat, email and Google.

    $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 property 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.

  • PMS API access: Included in some PMS plans and an add-on in others.
  • n8n: Free self-hosted Community edition, or n8n Cloud from about €20 a month (Starter) or €50 (Pro), billed annually.
  • Messaging: WhatsApp at Meta's own rates; Twilio US SMS at about $0.0083 per segment plus carrier fees if texts are used.
  • AI usage and email tools: Pay-per-use model fees and the email provider's own plan.

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 hotels & b&b?

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