AI Deploy Network
Healthcare ProvidersChatbotAI Case Study

How I Built a 5-Workflow WhatsApp Automation System for a Clinic

AI Deploy Network Approved

Built a fully automated patient communication system for a clinic using 5 connected n8n workflows. The system handles intake, appointment confirmation, reminders, follow-ups, and FAQ responses entirely through WhatsApp without staff involvement.

Nora AnabiriBy Nora Anabiri
Chapter 01

The Business Challenge

The business situation the organisation faced before the project began.

The clinic managed all patient communication manually via phone and WhatsApp. Staff handled appointment scheduling, reminders, and basic inquiries by hand, creating bottlenecks during peak hours and causing missed follow-ups.

Chapter 03

How the Solution Was Delivered

Discovery, design, development, testing and rollout — the journey, not the tooling.

  1. 1Mapped the full patient communication journey from intake to post-visit
  2. 2Built Supabase schema to store patient records and appointment data
  3. 3Built intake frontend on Lovable connected to Supabase
  4. 4Built 5 n8n workflows sequentially and tested each in isolation
  5. 5Connected GreenAPI webhook for live WhatsApp delivery
  6. 6Tested end-to-end flow across all 5 workflows before deployment
Business Impact

Business Outcomes & Impact

The measurable outcomes from the underlying AI Deployment — with the story behind them.

Hours Automated
30
Cost Savings
Currency not specified
Revenue Impact
Currency not specified
Measurable Business Outcome

Automated 5 distinct patient communication workflows, reducing manual staff intervention across the full appointment lifecycle from intake to post-visit follow-up.

Business Outcome Categories

Productivity ImprovementCustomer ExperienceTime Savings

The story behind the numbers

Fully automated the patient communication cycle from intake to post-visit follow-up. Eliminated manual reminder sending. Reduced missed appointments through timely automated WhatsApp notifications sent 24 hours in advance.

Reflection

Lessons Learned

What surprised the team, what worked well, and what would be done differently.

  • Building workflows sequentially and testing each in isolation before connecting them prevents compounding errors
  • Supabase RLS must be disabled during development or n8n insert operations will silently fail
  • Lovable frontend forms need explicit field validation before Supabase insertion to avoid dirty data