Case Study

Case Study: Supplement Brand Claims & Retention Automation

We built a connected set of automations for a direct-to-consumer supplement brand selling on Shopify with subscriptions: one customer profile with lifecycle flows, a claims pre-check against an approved library, subscription retention with an honest cancel path, an AI support agent that routes possible adverse events to a person, and proactive order-status and returns handling. The support team now spends its time on conversations that need a person, and every claim has a traceable approval.

Brand type
Direct-to-consumer supplement brand with subscribe-and-save
Team involved
Founder, ecommerce lead, support team, regulatory lead, quality lead
Systems connected
Shopify, Recharge, Klaviyo, Gorgias, ShipStation, n8n
Delivery
Scrum, 1-week sprints, about 9 weeks to full launch

The challenge

Where the practice started

Approved claims lived in a spreadsheet, and copy for emails, product pages and influencer briefs was reviewed by email under deadline. Nobody could show who had approved a given sentence.

Subscribers cancelled through the portal, by email and through support, and the reasons were never recorded. Many cancellations turned out to be customers with product left over.

The support inbox was dominated by order-status and subscription questions, and messages that mentioned a reaction were handled in the same queue as everything else.

Lifecycle emails were a single welcome series from launch, with no replenishment timing and no link to subscription status or support history.

Goals

What the project had to change

  • Every claim used in marketing traces back to an approved library entry.
  • Every possible adverse event reaches a trained person straight away, with details preserved.
  • Subscribers can skip, delay or cancel easily, and the brand knows why they leave.
  • Order-status questions are answered instantly or before they are asked.
  • Lifecycle flows run from one customer profile and approved wording.

What we built

What we built, as one connected system.

01

Claims pre-check

We structured the approved claims into a library by market with evidence links, and every draft page, email and brief now goes through a pre-check and the regulatory lead's sign-off with an audit trail.

Service details
02

AI support agent

An agent inside the help desk that screens every message for possible adverse events first, answers routine questions from approved product information and handles allowed order and subscription actions.

Service details
03

Subscription retention

Cancel reasons captured, skip and delay options shown alongside a visible cancel button, renewal reminders and polite failed-payment messages.

Service details
04

Order status and returns

Proactive shipping updates and delay alerts from tracking events, instant order-status answers and a returns form that collects lot numbers for the quality lead.

Service details
05

Customer CRM and lifecycle flows

One profile in Klaviyo with welcome, how-to-use and replenishment flows timed to pack size, each template tagged with approved claim IDs.

Service details

Architecture

How the brand's workflows connect

Shopify Orders, products Recharge Subscriptions Gorgias Tickets n8n Five workflows AI steps Screen, match Claims library Approved wording Klaviyo Email and SMS Support team Queues Regulatory lead Claims, AEs Logs and reports Audit trail
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 Orders, subscription events and support tickets feed one n8n instance.
  2. 2 Five workflows screen messages, match copy to the claims library and send lifecycle and service messages through Klaviyo.
  3. 3 The support team works short queues; the regulatory lead signs off claims and assesses possible adverse events.
  4. 4 Every decision and message is logged, and weekly reports show the measures the brand 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 customers see

  • Proactive shipping updates and fast answers
  • Skip, delay and cancel options side by side
  • A person following up quickly if they mention a reaction
  • Helpful, consistently worded emails timed to their pack size

What the team sees

  • Adverse event flags at the top of the queue
  • Only flagged claims to review, with evidence links
  • Cancel reasons and damage reports grouped by product and lot
  • A weekly report on repeat purchase and support load

What the automation does

  • Screens, answers, reminds and routes on schedule
  • Applies consent, opt-outs and market rules across every workflow
  • Logs every step and alerts the ecommerce lead if anything fails

Edge cases and fallbacks

A cancellation email mentions feeling unwell
Routed to the adverse event handler first, then processed as a cancellation.
A claim is withdrawn
Every template and page using it is flagged and paused.
A customer opts out in one workflow
One shared opt-out list stops messages from every workflow.
The AI provider is unavailable
Tickets stay with people, and adverse event keywords still trigger a basic alert.
Carrier tracking feed outage
Updates pause rather than send stale status, and the team is alerted.

Integrations

What we connected

All integrations

Shopify

Store platform

Orders, customers, products and fulfilment events for every workflow.

Shopify Admin API and webhooks.

Recharge

Subscriptions

Renewals, skips, failed payments and cancellations.

Recharge API and webhooks, verified with HMAC signatures.

Klaviyo

Email and SMS

Customer profiles, events, segments and lifecycle flows.

Klaviyo API with a private key or OAuth.

Gorgias

Help desk

Tickets, messages, AI drafts and adverse event flags.

Gorgias REST API with an API key from account settings.

ShipStation

Shipping

Shipments and tracking events for proactive updates.

ShipStation API v2 and tracking webhooks.

Slack and Microsoft Teams

Team alerts

Adverse event flags, claims sign-off requests 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 reviewed the claims spreadsheet, ticket categories, cancel flow and fulfilment setup, mapped the adverse event procedure with the regulatory lead and agreed data flows.

  2. 02

    Library and access

    Week 2

    Structured the approved claims library by market, set up API access to Shopify, Recharge, Klaviyo, Gorgias and ShipStation, and approved message templates.

  3. 03

    Sprint 1: claims pre-check

    Week 3

    Built intake, matching, routing and the audit trail; recent copy was run through it beside the regulatory lead's own review.

  4. 04

    Sprint 2: support safety screen

    Week 4

    The pre-check went live. Built the adverse event screen and hand-off in the help desk before any automated answers.

  5. 05

    Sprint 3: AI answers

    Week 5

    The screen went live. Built the approved product knowledge base and order actions in draft mode for agents.

  6. 06

    Sprint 4: subscriptions

    Week 6

    Drafts were reviewed daily. Built cancel reasons, skip and delay options, reminders and payment recovery.

  7. 07

    Sprint 5: order status

    Week 7

    Subscriptions went live. Built tracking updates, delay alerts and the returns form with lot numbers.

  8. 08

    Sprint 6: CRM flows

    Week 8

    Order status went live. Built the merged profile and lifecycle flows with claim IDs.

  9. 09

    UAT and handover

    Week 9

    The team ran acceptance tests, direct AI replies were enabled for approved categories, and we handed over run books.

  10. 10

    Support

    Ongoing

    Weekly review of safety flags during stabilisation, then monthly care.

Who does what

What the team does, and what automation does.

Automation does

  • Pre-checks copy against the approved claims library
  • Screens every support message for possible adverse events
  • Answers routine questions from approved product information
  • Sends subscription reminders and shows skip, delay and cancel options
  • Sends shipping updates and collects returns with lot numbers
  • Runs lifecycle flows from one customer profile

The team does

  • Revise flagged copy to approved wording
  • Handle support hand-offs and edits
  • Approve returns, replacements and refunds
  • Answer subscription questions that need a person

Regulatory lead or founder decides

  • Approves, changes or rejects every new claim
  • Assesses possible adverse events and decides on FDA reporting
  • Decides batch investigations with the quality lead
  • Approves subscription terms and retention offers

Compliance handled

Privacy, consent and safety, built in.

No medical advice from automation

Medical questions get a fixed reply and a person follows up.

Adverse event routing

Possible adverse events go to a trained person at once, supporting the 15-business-day FDA reporting window for serious reports and six-year record keeping.

Source: www.fda.gov

Claims from the approved library only

Every claim traces to an approved entry, in line with FTC substantiation expectations.

Source: www.ftc.gov

Structure/function disclaimer

Label claims repeated online carry the FDA disclaimer.

Source: www.fda.gov

Easy cancellation

The cancel option stays visible beside any offer, in line with ROSCA and California's automatic renewal law.

Source: www.law.cornell.edu

AI disclosure

The support agent says it is automated, matching Article 50 of the EU AI Act.

Source: artificialintelligenceact.eu

Outcomes

What changed for the practice

  • Every claim in marketing now traces to an approved library entry with a named approver.
  • Messages that could describe an adverse event reach a trained person straight away.
  • Subscribers can skip or delay in one click, and the brand now knows why people cancel.
  • Most order-status questions are answered instantly or before customers ask.
  • Damage reports are grouped by lot, so the quality lead sees patterns early.
  • Lifecycle emails run from one customer profile and consistent, approved wording.

What we track

The measures the practice watches.

Claims review

Drafts flagged, time to sign-off and live content drift found by the sweep.

Adverse event handling

Time from message to human review for every flagged case.

Subscription churn

Monthly churn by cohort, cancel reasons and skip and delay usage.

Support load

WISMO tickets per hundred orders and tickets resolved without hand-off.

Repeat purchase

Time to second order and repeat-purchase rate by product line.

Returns quality

Damage reports by lot and time to resolution.

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, claims library structure, data flows and the backlog.

    $1,000 – $2,000

  • Claims pre-check module

    Library, matching, routing and audit trail.

    $700 – $1,500

  • AI support module

    Safety screen, knowledge base, actions and hand-offs.

    $2,500 – $5,000

  • Subscription module

    Cancel reasons, options, reminders and recovery.

    $700 – $1,500

  • Order status module

    Tracking updates, delay alerts and returns intake.

    $600 – $1,300

  • CRM flows module

    Merged profile and lifecycle flows.

    $700 – $1,500

  • Integrations

    Shopify, Recharge, Klaviyo, Gorgias and ShipStation 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 support agent. Every brand 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.

  • Shopify and apps: Each vendor's own plan (Shopify, Recharge, Klaviyo, Gorgias, ShipStation).
  • n8n: Free self-hosted Community edition, or n8n Cloud from about €20 a month (Starter) or €50 (Pro), billed annually.
  • AI usage: Pay-per-use model fees, depending on ticket and content volume.

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 health & supplement brand?

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
Sources we checked

Rules and product facts on this page come from these pages, checked in November 2026. This is general information, not legal advice; confirm the rules that apply to your practice with your own adviser.