Compare
CaseNotes vs Fashionly vs WDDNG
The problem, what was built, the stack and the outcome, next to each other.
Clear · Up to 3 at a time
In common
- Shared stack: Next.js, LangGraph
- Both kinds of work: AI, Web, Mobile
- Order: WDDNG (Jan 2026 – present) → CaseNotes (Feb 2026 – present) → Fashionly (Apr 2026 – present)
Swipe sideways to compare ›
CaseNotes ›
South African legal research, e-discovery and learning, powered by AI
Fashionly ›
Your style, elevated: an AI stylist that starts with what you own
WDDNG ›
South Africa's wedding marketplace, with two apps on Google Play
At a glance
- Role
- Founder / Lead Engineer
- When
- Feb 2026 – present
- Length
- 9 mo so far
- Status
- Live
- Type
- AI, Web, Mobile
- Role
- Founder / Lead Engineer
- When
- Apr 2026 – present
- Length
- 7 mo so far
- Status
- MVP
- Type
- AI, Mobile, Web
- Role
- Founder / Full-stack & Mobile Engineer
- When
- Jan 2026 – present
- Length
- 10 mo so far
- Status
- Live
- Type
- AI, Mobile, Web
The problem
South African legal information is scattered across portals with limited keyword search, while international e-discovery platforms are often priced beyond the local market.
Fashion-commerce recommendations usually optimise for another purchase without understanding what the customer already owns.
South African couples plan across fragmented directories, WhatsApp messages and opaque “price on request” listings, while many international tools don't support local multi-ceremony wedding journeys.
What was built
An integrated research, e-discovery and learning platform: hybrid semantic search across more than 10,000 judgments, a precedent citation graph, structured document extraction, AI-assisted discovery and stateful research workflows.
Fashionly grounds recommendations in the user's wardrobe, builds outfits from existing items and recommends products only where a genuine wardrobe gap exists. Khanya, a LangGraph stylist with about 15 typed tools, handles wardrobe access, catalogue search, saved looks and human-stylist bookings.
A Next.js and Supabase marketplace with two Kotlin / Jetpack Compose Android apps on Google Play: one for couples, one for vendors. Thuli, the AI planner, is a LangGraph supervisor coordinating 16 specialist agents.
Stack
- Next.js
- FastAPI
- PostgreSQL
- pgvector
- Neo4j
- Redis/ARQ
- Azure OpenAI
- LangChain
- LangGraph
- Next.js
- Kotlin
- Supabase
- LangGraph
- MongoDB
- SSE
- Next.js
- Supabase
- PostgreSQL
- Kotlin
- Jetpack Compose
- LangGraph
- Zod
- Paystack
- Azure
- LangSmith
Highlights
- Five-stage Graph RAG pipeline in LangGraph
- Hybrid pgvector and Neo4j retrieval, and a TAR active-learning loop
- Human-in-the-loop tool-calling chat with PostgreSQL checkpoints
- MCP server for case search and drafting
- Khanya: a LangGraph tool-calling stylist with about 15 typed tools
- MongoDB-checkpointed conversation memory and SSE streaming of tool progress and grounded product cards
- Request-scoped Supabase clients with row-level security on every request
- Two Kotlin / Jetpack Compose Android apps published on Google Play
- Thuli: a LangGraph supervisor coordinating 16 specialist agents through Zod-typed handoff tools
- Per-agent model selection, token metering and LangSmith tracing
- SSE streaming that renders vendor cards and progress during an answer
Infrastructure choices
- pgvector + Neo4j
- Redis / ARQ workers
- LangGraph with PostgreSQL checkpoints
- Supabase with RLS
- MongoDB checkpoints
- SSE
- Supabase with PostgreSQL RLS
Outcome
An integrated research and review platform grounded in more than 10,000 judgments, with a structured learning bank of 1,624 rubric-scored questions. The architecture supports resumable jobs, traceable sources and human review.
A working end-to-end MVP across web and Android: wardrobe management, catalogue discovery, conversational styling, saved looks and human-stylist booking.
The marketplace runs across web and two production Android apps, giving couples structured planning tools and vendors better-qualified enquiries with date, budget and guest-count context.