Compare
Multichoice installer payments vs CV Coach 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: none in common
- Order: CV Coach (2025 – present) → Makunike.com AI Twin (Oct 2026)
Swipe sideways to compare ›
Multichoice installer payments ›
R5M+ paid to installers in the first six months
CV Coach ›
AI CV analysis, job matching and tailored applications
Makunike.com AI Twin ›
This website: a portfolio you can interview by phone call or chat
At a glance
- Role
- Integration engineer
- When
- Delivered
- Length
- —
- Status
- Delivered
- Type
- Platform
- Role
- Founder / Lead Engineer
- When
- 2025 – present
- Length
- 1 yr 9 mo so far
- Status
- MVP
- Type
- AI, Web
- Role
- Designer & Engineer
- When
- Oct 2026
- Length
- 1 mo
- Status
- Live
- Type
- AI, Web
The problem
Integrated the installer management system into Multichoice's payment process so installers are paid accurately and on time.
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.
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 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.
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
- Payments integration
- FastAPI
- Next.js
- Supabase
- LangGraph
- LangChain
- Celery
- 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
- Processed over R5 million in installer payments within six months
- LangGraph workflow with custom tools to parse, compare evidence and score the match
- Asynchronous analysis pipeline
- 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
—
—
- Vercel serverless (Next.js route handlers)
- Azure OpenAI
- Supabase Postgres + pgvector (HNSW)
- TypeSafe Jev
- Azure Blob Storage
Outcome
Over R5 million in installer payments processed within six months.
—
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.