A cosmetic adverse event reporting workflow that never lets a case slip
A possible reaction can arrive anywhere: a review, a DM, a support email or a returns note. We build a workflow that watches those inboxes for reaction language, opens a case for your safety contact with the order and batch attached, asks the customer standard follow-up questions you approved, tracks deadlines such as MoCRA's 15 business days for serious adverse events and keeps a dated log. A typical build costs $1,000 to $2,500 per workflow and takes about four weeks.
The problem
Why cosmetic adverse event reporting starts in the wrong inbox
Under MoCRA, the responsible person must report serious adverse events to FDA within 15 business days, with a copy of the label, and in the EU the responsible person and distributors must notify serious undesirable effects to the authority without delay. The clock starts when the brand receives the information, not when someone notices it.
Yet reaction reports are scattered. A one-star review saying "this burned my skin", an Instagram DM and a refund request with "rash" in the notes may all sit unseen by the safety contact for days, and nobody keeps a single log of what was received and done.
What we build
What our MoCRA adverse event reporting workflow includes
Inbox monitoring
Help desk, review feeds, social inboxes and returns notes scanned for reaction language you approve.
Case creation
A case for the safety contact with customer, product, order and batch details attached.
Standard follow-up
Your approved questions sent to the customer, with no advice given.
Deadline tracker
Business-day countdowns for the reporting timelines your regulatory lead sets per market.
Marketing pause
The customer is suppressed from marketing until the case closes.
Case log and trends
A dated log of every case and a monthly view by product and batch.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Mention detected
A message, review or note mentions a possible reaction.
-
02
Automated
Case opened
The case is created with order and batch data and the customer gets an acknowledgement.
-
03
Automated
Follow-up sent
Approved follow-up questions go to the customer.
-
04
Team review
Care team checks
Customer care confirms details and adds anything missing.
-
05
Founder or regulatory lead decides
Seriousness and reporting
Whether an event is serious and whether to report it is decided by the safety contact or regulatory lead.
How it behaves
How adverse event intake behaves
What the customer sees
- A calm, prompt acknowledgement
- A few clear follow-up questions
- A named way to reach the team
What the safety contact sees
- Every possible case in one log with order and batch
- Deadline countdowns per case
- Monthly trends by product and batch
What the automation does
- Scans every inbox for reaction language
- Opens cases and pauses marketing
- Logs every step with dates
Edge cases and fallbacks
- Reaction mentioned in a public review
- Case opened; any public reply is drafted for approval and reveals no personal details.
- No order can be matched
- Case opened anyway with a request for the batch code.
- Same customer reports twice
- Merged into one case with both messages.
- Monitoring or help desk outage
- A daily catch-up scan runs after recovery and the safety contact is alerted.
Architecture
Adverse event intake for a beauty brand at a glance.
- Input
- Logic and services
- AI step
- Data
- People
- Output
How it flows
- 1 Messages, reviews and notes from every inbox are scanned by n8n.
- 2 Possible reaction mentions are flagged using terms your safety contact approved.
- 3 A case is logged with order and batch data, and the customer gets an acknowledgement and follow-up questions.
- 4 The safety contact decides seriousness and any report, with the deadline shown on the case.
Project planner
How the project runs, phase by phase.
Adverse event & complaint intake project plan
Typical time to launch: about 4 weeks, then support
-
01
Discovery
2 to 3 days
Inboxes, current complaint handling, markets, reporting responsibilities and wording.
-
02
Design
2 to 3 days
Reaction terms, case fields, follow-up questions, deadlines and access controls.
-
03
Build
1 to 2 weeks
Monitoring, case creation, follow-ups, deadline tracker and reports.
-
04
Shadow run
About 1 week
Past months of messages scanned and flags compared with the safety contact's review.
-
05
Launch
1 to 2 days
Switch on live monitoring and acknowledgements.
-
06
Support
Ongoing
Term tuning, new channels and rule updates.
What it runs on
Real products only, connected through the access each vendor provides. See all integrations
Cost estimate
What it costs, line by line.
-
Discovery and design
Terms, case fields, deadlines and access.
$200 – $400
-
Build
Monitoring, case creation, follow-ups and tracker.
$500 – $1,300
-
Integrations
Help desk, reviews, store and batch data.
$150 – $400
-
Testing and shadow run
Historical scan compared with manual review.
$100 – $250
-
Launch and training
Switch-on and safety contact walkthrough.
$50 – $150
-
Total project estimate
$1,000 – $2,500
Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Social inbox access depends on each platform's API. Help desk and n8n costs are billed to you 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.
- Help desk and reviews: Your Gorgias, Zendesk and reviews app plans.
- n8n and AI usage: n8n Cloud from about €20 a month (Starter, billed annually) or self-hosted; AI flagging billed per use.
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
Privacy and consent
Rules we design for, with the sources.
US: MoCRA serious adverse events
Responsible persons must report serious adverse events to FDA within 15 business days with a copy of the label, and new information within a year also within 15 business days.
Source: www.fda.govEU: serious undesirable effects
Article 23 of Regulation 1223/2009 requires the responsible person and distributors to notify the competent authority without delay, with the product name and corrective measures.
Source: eur-lex.europa.euEU and UK: health data
Reaction reports are health data under Article 9 GDPR and UK GDPR, so the case log has restricted access and minimal fields.
Source: gdpr-info.euFree tools
Try these first, free.
Guides to read first
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 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 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 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 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
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
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
FAQ
Adverse event & complaint intake questions, answered.
MoCRA requires the responsible person to report serious adverse events to FDA within 15 business days of receiving the information, with a copy of the label. Your regulatory lead decides what is serious; our workflow makes sure every possible case reaches them quickly with the facts.
No. It flags possible reaction language and opens a case. Seriousness and reporting are decisions for your safety contact or regulatory lead.
No. We prepare the case data in a clean format; your team files through the official route.
Help desk email and chat, review platforms with an API such as Okendo, returns notes and social inboxes where the platform API allows, confirmed per project.
A calm acknowledgement, your approved follow-up questions and how to reach your team. It never gives medical advice; serious symptoms get your instruction to seek medical help.
Time from first mention to case opened, time to safety contact review, cases by product and batch and any case that approached a deadline.
Free 20-minute call
Want this for your beauty & cosmetic?
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.
More for beauty & cosmetics
All servicesBeauty CRM & replenishment flow automation
One customer profile across store, subscriptions, reviews and support, with replenishment reminders timed to each product's real usage, shade-aware cross-sell and flows that pause when a customer reports a problem.
From $1,000 · About 4 weeks Details
INCI & product data enrichment
Keep INCI lists, shade names, sizes, warnings and claims identical across your store, marketplaces, retailer templates and regulatory records, with every difference flagged before it goes live.
From $1,000 · About 4 to 5 weeks Details
Batch, expiry & logistics automation for beauty
Line up lot numbers, expiry dates and shipments between your store, 3PL and batch records, catch short-dated stock before it ships, answer order status questions and be ready to trace any batch fast.
From $1,000 · About 4 weeks Details