Compare

Makunike.com AI Twin vs ParcelNow 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: Next.js
  • Both kinds of work: Web
  • Order: ParcelNow (2025 – 2026) → CaseNotes (Feb 2026 – present) → Makunike.com AI Twin (Oct 2026)

Swipe sideways to compare ›

Makunike.com AI Twin ›

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

ParcelNow ›

On-demand parcel delivery with real-time tracking

CaseNotes ›

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

At a glance

Role
Designer & Engineer
When
Oct 2026
Length
1 mo
Status
Live
Type
AI, Web
Role
Technical lead, Smart Kitchen Co
When
2025 – 2026
Length
1 yr
Status
Delivered
Type
Web, Platform
Role
Founder / Lead Engineer
When
Feb 2026 – present
Length
9 mo so far
Status
Live
Type
AI, Web, Mobile

The problem

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.
Customer and operations dashboards with backend services for parcel lifecycles, tracking events and notifications, built for high-throughput transactional workflows.
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

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.
—
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

  • 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
  • Next.js
  • FastAPI
  • PostgreSQL
  • Redis
  • Docker
  • Next.js
  • FastAPI
  • PostgreSQL
  • pgvector
  • Neo4j
  • Redis/ARQ
  • Azure OpenAI
  • LangChain
  • LangGraph

Highlights

  • 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
  • Next.js dashboards over FastAPI services
  • Live delivery updates through logistics and messaging 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

Infrastructure choices

  • Vercel serverless (Next.js route handlers)
  • Azure OpenAI
  • Supabase Postgres + pgvector (HNSW)
  • TypeSafe Jev
  • Azure Blob Storage
  • Docker-based development and deployment standards
  • pgvector + Neo4j
  • Redis / ARQ workers
  • LangGraph with PostgreSQL checkpoints

Outcome

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.
—
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.

See it