Compare
CV Coach vs CaseNotes vs OrderEase
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: FastAPI, Next.js
- Both kinds of work: Web
- Order: CV Coach (2025 – present) → OrderEase (2025 – 2026) → CaseNotes (Feb 2026 – present)
Swipe sideways to compare ›
CV Coach ›
AI CV analysis, job matching and tailored applications
CaseNotes ›
South African legal research, e-discovery and learning, powered by AI
OrderEase ›
Branded online ordering for restaurants and retailers
At a glance
- Role
- Founder / Lead Engineer
- When
- 2025 – present
- Length
- 1 yr 9 mo so far
- Status
- MVP
- Type
- AI, Web
- Role
- Founder / Lead Engineer
- When
- Feb 2026 – present
- Length
- 9 mo so far
- Status
- Live
- Type
- AI, Web, Mobile
- Role
- Technical lead, Smart Kitchen Co
- When
- 2025 – 2026
- Length
- 1 yr
- Status
- Live
- Type
- Web, Platform
The problem
A Chrome extension captures job ads; a LangGraph workflow parses the CV and the ad, scores the match and drafts tailored cover letters and CV revisions.
South African legal information is scattered across portals with limited keyword search, while international e-discovery platforms are often priced beyond the local market.
Direct ordering and order management: menus, orders, payments and fulfilment, with automated order intake and status updates that cut merchants' operational overhead.
What was built
A Chrome extension captures advertisements, stores them in PostgreSQL and queues analysis. The platform compares a CV with a job description, produces a structured match score and generates tailored cover letters and CV revisions.
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
- FastAPI
- Next.js
- Supabase
- LangGraph
- LangChain
- Celery
- Next.js
- FastAPI
- PostgreSQL
- pgvector
- Neo4j
- Redis/ARQ
- Azure OpenAI
- LangChain
- LangGraph
- Next.js
- FastAPI
- PostgreSQL
- Redis
Highlights
- LangGraph workflow with custom tools to parse, compare evidence and score the match
- Asynchronous analysis pipeline
- 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
- Fast, responsive ordering on Next.js
- FastAPI services for menus, orders, payments and fulfilment
Infrastructure choices
—
- pgvector + Neo4j
- Redis / ARQ workers
- LangGraph with PostgreSQL checkpoints
—
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.
—