All Projects
Live2025AI/ML ยท Education ยท Community Impact

K53 Drill Master

AI-Powered Driving Test Prep Tackling South Africa's 60% Failure Rate

Adaptive AI learning platform for South Africa's K53 driving test. Gamified preparation with personalized feedback, progress tracking, and real-time performance analytics โ€” turning a 60% failure rate into confident drivers.

Serving

500K+ learner drivers annually

Market

60%+ K53 failure rate addressed

Problem

Lack of quality prep resources

Result

50+ paying subscribers, 4.8/5 rating

The Problem

What needed solving

Over 60% of South Africans fail the K53 learner's licence test due to lack of accessible, quality preparation resources. This creates barriers to employment, mobility, and economic participation for millions.

The Solution

How I built it

An AI-driven preparation platform with adaptive question selection, detailed explanations, progress analytics, and a gamified learning experience. The AI adapts difficulty based on individual performance patterns.

Tech Stack & Decision Rationale
01

Next.js 14

Fast, SEO-optimized study platform

02

TypeScript

Robust adaptive learning logic

03

OpenAI API

Adaptive learning & personalized feedback

04

Supabase

User progress & question database

05

Tailwind CSS

Mobile-first responsive design

README.md โ€” k53-drill-master
๐Ÿ“„ README.md
# K53 Drill Master
> AI-Powered Driving Test Prep Tackling South Africa's 60% Failure Rate

## Project Context
**Category:** AI/ML ยท Education ยท Community Impact
**Status:** Live ยท 2025
**Author:** Nandawula Regine Kabali-Kagwa โ€” East London, South Africa

## Stack
```
Next.js 14                     # Fast, SEO-optimized study platform
TypeScript                     # Robust adaptive learning logic
OpenAI API                     # Adaptive learning & personalized feedback
Supabase                       # User progress & question database
Tailwind CSS                   # Mobile-first responsive design
```

## Architecture Notes
- All data mutations validated server-side via Next.js API routes
- Row-Level Security enforced at database level (Supabase)
- Mobile-first, PWA-ready, offline-tolerant where connectivity is unreliable
- PayFast integration for ZAR-native payments (no USD conversion)
- SEO-optimised: metadata, JSON-LD, canonical URLs, sitemap

## Environment Variables
```env
NEXT_PUBLIC_SUPABASE_URL=
NEXT_PUBLIC_SUPABASE_ANON_KEY=
SUPABASE_SERVICE_ROLE_KEY=
OPENAI_API_KEY=
NEXT_PUBLIC_PAYFAST_MERCHANT_ID=
NEXT_PUBLIC_PAYFAST_MERCHANT_KEY=
RESEND_API_KEY=
```

## Links
- ๐ŸŒ Live:   https://nanda-k53-drill-master.vercel.app/
- ๐Ÿ™ GitHub: https://github.com/Nanda-Regine/nanda-k53-drill-master
- ๐Ÿ—๏ธ Portfolio: https://creativelynanda.co.za/projects/k53-drill-master

---
Built from East London, South Africa ยท 5th Industrial Revolution

Interested in similar work?

Let's discuss how I can build something like this for your business.

Let's Talk