Case study · Healthcare
A clinic operations platform with AI-assisted administration
A full-stack web platform for a clinic to manage patient records, appointments, and administrative workflows, with AI used to prepare documentation for staff review.
- Client
- Confidential Client
- Industry
- Healthcare
- Year
- 2024
- Services
- Web Development, Generative AI, AI Integration
Business challenge
The problem
The clinic relied on manual data entry across disconnected tools for patient records, appointments, and administrative documentation. This created duplicate work and made information hard to find when it was needed.
Existing workflow
- Patient details re-entered in several places
- Appointments managed separately from records
- Administrative documents drafted manually
Solution
What we built
We built a web platform that brings patient records, scheduling, and administrative workflows into one system with role-based access.
A language model integration prepares draft administrative documentation and summaries from structured record data. Drafts are presented to staff and clinicians for review and editing before they are saved — the AI does not make clinical decisions.
Architecture
System overview
- 1
Records
Structured patient and visit data.
- 2
Scheduling
Appointments linked to records.
- 3
AI drafting
Summaries prepared from record data.
- 4Human
Staff review
Drafts edited and approved.
- 5
Saved
Approved documents stored with history.
Product experience
- Single view of patient record, history, and upcoming appointments
- Draft documents clearly marked as AI-prepared until approved
- Role-based screens for front desk and clinical staff
Outcome
- Records, scheduling, and administrative workflows consolidated into one platform
- AI-prepared drafts integrated into a human review step
- Client-approved performance figures are not published
Integrations
- Supabase (database and auth)
- OpenAI API for drafting
Technology
- Next.js
- Python
- Supabase
- OpenAI
Lessons learned
What we took away
01
In healthcare, the review step is part of the product: designing it well determines whether AI drafting is actually used.
02
Consolidating data first made the AI features possible; AI on top of fragmented data would have added little.
More work
Other case studies
Healthcare · 2024
Ilaaj AI — an AI-assisted health web app designed for low-resource settings
A browser-based healthcare application combining AI-assisted image screening, a symptom-intake assistant, and voice guidance, designed for clinics with limited specialist access and users with varying literacy.
E-commerce · 2024 · Confidential client
Behaviour-based product recommendations for an online retailer
A recommendation engine that uses browsing and purchase behaviour to suggest relevant products, served through an API into the retailer's storefront.
Next step
Have a similar problem?
Tell us about the workflow, the systems involved, and what you want to change. We'll tell you honestly what a first build could look like.
What happens next
- 1Tell us about one workflow
- 2We review it before replying
- 3A working session, then a first-build proposal