Case Study

Case Study: Gym Membership & Retention Automation

We built a connected set of automations for an independent fitness club with a gym floor, group classes and personal training: a lead-to-member pipeline in a CRM, an AI assistant on the website and Instagram, attendance-based retention alerts, failed payment recovery and a single queue for freezes and cancellations. Advisors and coaches now work from short lists instead of scattered inboxes, and the manager only sees what needs a decision.

Club type
Independent gym with group classes and personal training
Team involved
Club manager, membership advisors, front desk, coaches
Systems connected
Club management platform, Stripe, CRM, Meta lead forms, Twilio, n8n
Delivery
Scrum, 1-week sprints, about 9 weeks to full launch

The challenge

Where the practice started

Leads arrived from Facebook and Instagram ads, the website and walk-ins and were followed up when an advisor had time. Trial visitors who did not join on the day were rarely contacted again, and nobody could say which campaign produced members.

The same questions about prices, classes and freezing arrived in Instagram messages late at night and waited until morning.

Attendance data sat in the club platform unused. Coaches noticed missing faces but had no list and no record of who had been contacted.

Failed payments were exported and chased by hand after every billing run, and freeze or cancellation requests came through four channels with answers that depended on who was on shift.

Goals

What the project had to change

  • Every lead gets a reply within minutes and every trial visitor gets a personal follow-up.
  • Routine questions are answered at any hour from approved wording, with health questions going to coaches.
  • Coaches get a weekly list of members whose attendance has dropped.
  • Failed payments are followed up politely and consistently after every billing run.
  • Every freeze and cancellation request is handled by the same rules and confirmed promptly.

What we built

What we built, as one connected system.

01

Lead-to-member pipeline

We connected Meta lead forms, website forms, walk-in sign-ups and missed calls to one CRM pipeline with instant replies, trial reminders, advisor tasks after each trial and a weekly source report.

Service details
02

AI assistant on web and Instagram

An assistant that answers from the club's approved library, offers trial slots from the live timetable, says it is automated and hands injuries, billing and cancellations to staff.

Service details
03

Retention alerts

A weekly comparison of each member's visits with their own habit, a first-month journey for new joiners and a ranked check-in list for coaches with drafted messages.

Service details
04

Failed payment recovery

Stripe failures open a case, members get a secure update link timed around Smart Retries, and open cases reach a private desk list with suspensions left to the manager.

Service details
05

Freeze and cancellation queue

Requests from every channel land in one queue, contract terms are pulled from the club platform, and staff send checked confirmations; members who joined online can cancel online.

Service details

Architecture

How the club's workflows connect

Ads, web, social Leads and chats Club platform Members, visits Stripe Failed payments n8n Five workflows AI assistant Answers, drafts CRM pipeline Stages and tasks Texts and emails Twilio, email Advisors, desk Lists, queues Club manager Decisions Log and reports Weekly summary
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 Leads and chats, member and visit data from the club platform, and failed payments from Stripe feed one n8n instance.
  2. 2 Five workflows update the CRM, send messages and use an AI step to answer questions and draft check-ins and confirmations.
  3. 3 Advisors, coaches and the desk work short lists and queues; the manager decides offers, suspensions and exceptions.
  4. 4 Every step is logged, and a weekly summary shows the measures the club 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 members and leads see

  • A reply with a trial link within minutes of enquiring
  • Answers to routine questions at any hour
  • A personal message from their coach if they have gone quiet
  • A polite update-your-card message instead of a surprise at the turnstile
  • A clear confirmation when they freeze or cancel

What staff see

  • One pipeline board, one coach list, one payments list and one request queue
  • Drafted messages and confirmations to check
  • A weekly report on leads, trials and joins by source

What the automation does

  • Captures, replies, reminds and drafts on schedule
  • Applies consent, opt-outs and quiet hours across every workflow
  • Logs every step and alerts the manager if anything fails

Edge cases and fallbacks

A member mentions an injury in a chat
No advice is given; a coach is alerted and replies personally.
A member opts out in one workflow
One shared opt-out list stops messages from every workflow.
A member pays at the desk mid-recovery
Staff mark it and pending reminders and retries stop.
The club platform API is unreachable
Runs are retried rather than built from stale data, and the manager is alerted.
Twilio or n8n has an outage
Requests are still logged, the chat falls back to a contact form and the manager gets an alert.

Integrations

What we connected

All integrations

Mindbody

Club and studio management

Clients, classes, class visits, sales and bookings for leads, retention and cancellations.

Mindbody Public API v6 and webhooks, with access granted for your site.

HubSpot

CRM

Contacts, deals, pipeline stages and follow-up tasks.

HubSpot CRM REST API.

Stripe

Payments

Failed subscription payments, retries and update links.

Stripe Billing API and webhooks such as invoice.payment_failed.

Twilio

SMS and voice

Lead replies, reminders, payment messages and opt-out handling.

Twilio Programmable Messaging and Voice APIs.

Google Business Profile

Local search

Trial booking link, messages and new-review alerts.

Google Business Profile settings and APIs.

Slack and Microsoft Teams

Staff alerts

Coach lists, hand-offs 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 9 weeks, then support

  1. 01

    Discovery

    Week 1

    We shadowed the desk and advisors, mapped leads, trials, billing and cancellations, collected real member questions and agreed data flows and consent wording.

  2. 02

    Design and access

    Week 2

    Approved message templates, pipeline stages, retention rules, cancellation rule table, club platform API access, Twilio number and A2P 10DLC registration.

  3. 03

    Sprint 1: lead pipeline

    Week 3

    Built and shadow-ran lead capture, replies and advisor tasks; demo and sign-off.

  4. 04

    Sprint 2: payments

    Week 4

    The pipeline went live. Built failed payment cases, messages and the desk list, run beside one billing cycle.

  5. 05

    Sprint 3: cancellations

    Week 5

    Payments went live. Built the request queue, contract lookup, confirmation drafts and the online cancellation form.

  6. 06

    Sprint 4: retention

    Week 6

    The queue went live. Built attendance alerts, the new-member journey and the coach list, reviewed by the manager first.

  7. 07

    Sprint 5: AI assistant

    Week 7

    Retention lists went to coaches. Built the answer library, website and Instagram assistant and hand-off rules.

  8. 08

    Assistant testing

    Week 8

    Ran real, tricky and health prompts; the manager signed off the library and hand-offs.

  9. 09

    UAT and handover

    Week 9

    The team ran acceptance tests on every workflow, the assistant went live, and we handed over run books and trained staff.

  10. 10

    Support

    Ongoing

    Weekly check-ins during stabilisation, then monthly care.

Who does what

What the team does, and what automation does.

Automation does

  • Captures every lead and replies with a trial link
  • Answers routine questions from the approved library
  • Builds the weekly attendance check-in list
  • Opens payment cases and sends update links
  • Collects freeze and cancellation requests and drafts confirmations

The team does

  • Follow up trial visitors personally
  • Contact drifting members and record outcomes
  • Talk privately with members about open payments
  • Check and send cancellation confirmations
  • Answer anything the assistant hands over

Manager or owner decides

  • Decides pricing, offers and contract exceptions
  • Approves suspensions, payment plans and fee waivers
  • Handles medical freezes, hardship and disputes
  • Approves the assistant's answer library

Compliance handled

Privacy, consent and safety, built in.

No health or training advice by chat

The assistant refuses health questions and alerts a coach.

Marketing texts in the US

Promotional texts only go to leads who gave prior express written consent; service replies stay separate.

Source: www.law.cornell.edu

Easy exit

Members who joined online can cancel online, in line with ROSCA and California's automatic renewal law.

Source: www.law.cornell.edu

AI disclosure

The assistant says it is automated on every channel, matching Article 50 of the EU AI Act.

Source: artificialintelligenceact.eu

Health data kept out of sales tools

PAR-Q and injury details stay in the club platform, not the CRM.

Source: gdpr-info.eu

Outcomes

What changed for the practice

  • Every lead now gets a reply with a trial link within minutes, day or night.
  • Trial visitors get a personal follow-up from an advisor who can see their goals.
  • Routine questions are answered at any hour, and health questions reach a coach.
  • Coaches get a short weekly list of members to check in with instead of guessing.
  • Failed payments are followed up the same polite way after every billing run.
  • Freeze and cancellation requests follow one set of rules with a full audit trail.

What we track

The measures the practice watches.

Lead response

Time to first reply and share of leads who book a trial.

Trial conversion

Trials attended and joins within two weeks, by source.

Retention list outcomes

Members contacted from the list and how many return to their usual pattern.

Payment recovery

Failed payments per run and share recovered after the first message and after retries.

Cancellation handling

Time from request to confirmation and number of disputes.

Assistant quality

Conversations resolved without hand-off and questions added to the library.

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

    Process mapping, data flows, wording and the backlog for all five services.

    $1,000 – $2,000

  • Lead pipeline module

    Capture, replies, advisor tasks and the source report.

    $700 – $1,500

  • AI assistant module

    Answer library, web and Instagram assistant, booking and hand-offs.

    $2,500 – $5,000

  • Retention module

    Attendance check, new-member journey and coach list.

    $700 – $1,500

  • Payments module

    Failure cases, update messages and the desk list.

    $600 – $1,300

  • Cancellation module

    Request queue, contract lookup, drafts and online form.

    $700 – $1,500

  • Integrations

    Club platform, Stripe, CRM, Meta and Twilio connections.

    $300 – $700

  • Testing, UAT and launch

    QA, acceptance testing, launch and training.

    $500 – $1,500

  • Total project estimate

    $7,000 – $15,000

Optional monthly care after launch is quoted with your proposal. Typical range for a project of this scope: four workflows plus an AI assistant. Every club 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 each way 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.
  • CRM and club software: Each vendor's own plan.
  • AI usage: Pay-per-use model fees, usually small at single-club volumes.

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 gyms & fitness?

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