Client workflow / pilot (In real use)

Dental Patient Reactivation System

Clinics have a list of patients who haven’t been back in a while. Everyone knows they should follow up. It almost never happens consistently, because it’s manual and there’s always something more urgent.

Status
Client workflow / pilot
Area
Lead Qualification & Appointment Booking, Sales & Outreach Automation
Workflow
5 steps · 3 failure paths
Stack

01 · Why it mattered

What the manual way was costing

  • Follow-ups were easy to skip on a busy week.
  • Without tracking, there was no way to see if follow-up was even working.

02 · System concept

What I set out to build

Find overdue patients automatically, send a follow-up that sounds personal, give them a booking link, and track bookings back into Airtable so the clinic can see what happened.

03 · Before / after

From manual steps to a system

Toggle between the manual process and the system. Click any step to see what it does, what tools it touches, and what happens if it goes wrong.

How it ran manually · depends on whoever is free

  1. 01Someone exports or scrolls the patient listby hand
  2. 02They try to work out who is overdueby hand
  3. 03Follow-ups are sent one by one, when there is timeby hand
  4. 04No clear view of who replied or bookedby hand

04 · Decision log

Why I built it this way

D-01Airtable as the clinic’s window

I wanted the clinic to see what the system was doing without logging into n8n. Airtable became the place they check who was contacted and who booked.

D-02Pilot before scaling

Running it as a pilot first means we can see how patients actually respond before turning it up.

05 · Reliability layer

What can go wrong, and who steps in

Where it happens
Step 01 Identify overdue patients
What goes wrong
Patient has no valid email
What the system does
Patient is skipped and flagged so staff can reach them another way.
Who handles it
A person: clinic staff

Human-in-the-loop points

  • Human in the loopPatient has no valid email → clinic staff
  • Human in the loopBooking can’t be matched to a patient → clinic staff

06 · Evidence

What exists today

  • Running as a client pilot.

07 · What this demonstrates

What this demonstrates

Making a follow-up process consistent and visible, so the clinic isn’t relying on memory or free time.

08 · Stack / integrations

What it’s built with

  • AirtablePatient list, contact status and booking visibility
  • GmailPersonalised follow-up emails
  • Cal.comBooking link and bookings
  • n8nOrchestration and tracking

Architecture · static view · 5 steps · 3 failure paths

    • → clinic staffPatient has no valid email
    • → system handlesEmail fails to send or bounces
    • → clinic staffBooking can’t be matched to a patient

More systems

Keep reading

Workflow build / tested scenarios

E-commerce Return Request Automation

Return requests are checked against the policy, recorded, and walked through to refund or replacement, with invalid ones going to manual review.

  1. Return request
  2. Eligibility check
  3. Return recorded
  4. Instructions sent
  5. Return tracked
  6. +1 more
3 failure paths · 3 human handoffs
Completed workflow

AI Cold-Outreach Draft Helper

Each prospect row in a sheet gets qualified and a personalised draft written back next to it, ready for a human to review and send.

  1. Prospect row
  2. Qualification
  3. Personalised draft
  4. Written back to sheet
  5. Human reviews & sends
3 failure paths · 3 human handoffs

Similar workflow?

Got a process that looks something like this?

Tell me how it runs today and where it hurts. If it’s a good fit for automation I’ll tell you how I’d approach it. If it isn’t, I’ll tell you that too.

Tell me what you’re trying to automate