Compare
Joel Transport vs CaseNotes vs Multichoice installer payments
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: Joel Transport (Dec 2022 – May 2023) → CaseNotes (Feb 2026 – present)
Swipe sideways to compare ›
Joel Transport ›
Online booking platform on AWS
CaseNotes ›
South African legal research, e-discovery and learning, powered by AI
Multichoice installer payments ›
R5M+ paid to installers in the first six months
At a glance
- Role
- Lead Engineer
- When
- Dec 2022 – May 2023
- Length
- 6 mo
- Status
- Live
- Type
- Web, Platform
- Role
- Founder / Lead Engineer
- When
- Feb 2026 – present
- Length
- 9 mo so far
- Status
- Live
- Type
- AI, Web, Mobile
- Role
- Integration engineer
- When
- Delivered
- Length
- —
- Status
- Delivered
- Type
- Platform
The problem
Centralised the customer journey and operational data, reduced manual hand-offs and set up a documented AWS foundation.
South African legal information is scattered across portals with limited keyword search, while international e-discovery platforms are often priced beyond the local market.
Integrated the installer management system into Multichoice's payment process so installers are paid accurately and on time.
What was built
Led architecture and hands-on engineering for an online booking platform: Python APIs and the AWS deployment architecture, integrated with Paystack, Sage Accounting, Zoho Bigin and Zoho SalesIQ.
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
- AWS
- Paystack
- Sage
- Zoho
- Next.js
- FastAPI
- PostgreSQL
- pgvector
- Neo4j
- Redis/ARQ
- Azure OpenAI
- LangChain
- LangGraph
- Payments integration
Highlights
- Python APIs and AWS deployment architecture
- Paystack, Sage Accounting, Zoho Bigin and Zoho SalesIQ integrations
- 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
- Processed over R5 million in installer payments within six months
Infrastructure choices
- AWS
- pgvector + Neo4j
- Redis / ARQ workers
- LangGraph with PostgreSQL checkpoints
—
Outcome
Centralised the customer journey and key operational data, reduced manual hand-offs and established a documented AWS foundation for future development.
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.
Over R5 million in installer payments processed within six months.