Compare
WhatsApp platforms vs Multichoice installer payments vs CaseNotes
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: none in common
- Order: WhatsApp platforms (2018 – 2022) → CaseNotes (Feb 2026 – present)
Swipe sideways to compare ›
WhatsApp platforms ›
Altur, Harambee and eButler on the WhatsApp Business API
Multichoice installer payments ›
R5M+ paid to installers in the first six months
CaseNotes ›
South African legal research, e-discovery and learning, powered by AI
At a glance
- Role
- Lead engineer, Mmogo Media
- When
- 2018 – 2022
- Length
- 4 yr
- Status
- Delivered
- Type
- Platform, AI
- Role
- Integration engineer
- When
- Delivered
- Length
- —
- Status
- Delivered
- Type
- Platform
- Role
- Founder / Lead Engineer
- When
- Feb 2026 – present
- Length
- 9 mo so far
- Status
- Live
- Type
- AI, Web, Mobile
The problem
A WhatsApp-based job platform (Altur), Harambee Youth Accelerator's move from a mobisite to WhatsApp, and eButler's WhatsApp ordering with payments through Flash.
Integrated the installer management system into Multichoice's payment process so installers are paid accurately and on time.
South African legal information is scattered across portals with limited keyword search, while international e-discovery platforms are often priced beyond the local market.
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.
Stack
- Python
- Django
- WhatsApp Business API
- Infobip
- Twilio
- Payments integration
- Next.js
- FastAPI
- PostgreSQL
- pgvector
- Neo4j
- Redis/ARQ
- Azure OpenAI
- LangChain
- LangGraph
Highlights
- Conversational journeys on the WhatsApp Business API
- Payments via Flash, Paystack and MTN MoMo
- Processed over R5 million in installer payments within six months
- 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
Infrastructure choices
—
—
- pgvector + Neo4j
- Redis / ARQ workers
- LangGraph with PostgreSQL checkpoints
Outcome
—
Over R5 million in installer payments processed within six months.
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.