Compare

WDDNG vs CaseNotes vs Makunike.com AI Twin

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
  • Both kinds of work: AI, Web
  • Order: WDDNG (Jan 2026 – present) → CaseNotes (Feb 2026 – present) → Makunike.com AI Twin (Oct 2026)

Swipe sideways to compare ›

WDDNG ›

South Africa's wedding marketplace, with two apps on Google Play

CaseNotes ›

South African legal research, e-discovery and learning, powered by AI

Makunike.com AI Twin ›

This website: a portfolio you can interview by phone call or chat

At a glance

Role
Founder / Full-stack & Mobile Engineer
When
Jan 2026 – present
Length
10 mo so far
Status
Live
Type
AI, Mobile, Web
Role
Founder / Lead Engineer
When
Feb 2026 – present
Length
9 mo so far
Status
Live
Type
AI, Web, Mobile
Role
Designer & Engineer
When
Oct 2026
Length
1 mo
Status
Live
Type
AI, Web

The problem

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.
South African legal information is scattered across portals with limited keyword search, while international e-discovery platforms are often priced beyond the local market.
Portfolios are static, but hiring conversations aren't. A recruiter wants to know whether I've shipped mobile apps, a hiring manager wants a production story in STAR form, and a sourcing agent wants structured answers it can compare. A PDF CV can't do any of that.

What was built

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.
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.
A digital version of me that holds a real interview by phone-style voice call or text, grounded only in material I curated. It changes what's on screen as it answers, logs what it can't answer so I can teach it, records and QA-scores every call, and is reachable by other AI agents over MCP and A2A.

Stack

  • Next.js
  • Supabase
  • PostgreSQL
  • Kotlin
  • Jetpack Compose
  • LangGraph
  • Zod
  • Paystack
  • Azure
  • LangSmith
  • Next.js
  • FastAPI
  • PostgreSQL
  • pgvector
  • Neo4j
  • Redis/ARQ
  • Azure OpenAI
  • LangChain
  • LangGraph
  • Next.js 15
  • React 19
  • Tailwind CSS v4
  • GPT-6.1 (Azure, Responses API)
  • gpt-realtime-2.1
  • WebRTC
  • text-embedding-3-small
  • Supabase pgvector
  • TypeSafe Jev
  • MCP
  • A2A
  • Azure Blob
  • LangSmith
  • Vercel

Highlights

  • 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
  • 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
  • Generative UI: the model calls typed navigate and show_panel tools, streamed to the browser as NDJSON events
  • Phone-call voice on gpt-realtime-2.1 over WebRTC, with every call recorded, transcribed and QA-scored
  • TypeSafe Jev in ten places: routing, tool selection, interview mode, guards, lead scoring, grounding, triage, FAQ review, agent vetting and call QA
  • Self-improving RAG: weak or ungrounded answers land in a ranked CMS inbox and become FAQs
  • MCP and A2A servers with request vetting and rate limits for agent-to-agent interviews

Infrastructure choices

  • Supabase with PostgreSQL RLS
  • pgvector + Neo4j
  • Redis / ARQ workers
  • LangGraph with PostgreSQL checkpoints
  • Vercel serverless (Next.js route handlers)
  • Azure OpenAI
  • Supabase Postgres + pgvector (HNSW)
  • TypeSafe Jev
  • Azure Blob Storage

Outcome

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.
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.
The twin never invents a fact about my career: when it doesn't know, it says so and I'm notified. Intent-matched navigation fires within about a second, before the first answer token. Every call is recorded, transcribed and scored so review starts with the calls that need it, and one knowledge base serves text, voice, MCP and A2A.

See it