Compare
Joel Transport vs Makunike.com AI Twin vs Pairly
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
- Both kinds of work: Web
- Order: Joel Transport (Dec 2022 – May 2023) → Pairly (Jul 2026 – present) → Makunike.com AI Twin (Oct 2026)
Swipe sideways to compare ›
Joel Transport ›
Online booking platform on AWS
Makunike.com AI Twin ›
This website: a portfolio you can interview by phone call or chat
Pairly ›
An AI-native operating system for founder-led teams
At a glance
- Role
- Lead Engineer
- When
- Dec 2022 – May 2023
- Length
- 6 mo
- Status
- Live
- Type
- Web, Platform
- Role
- Designer & Engineer
- When
- Oct 2026
- Length
- 1 mo
- Status
- Live
- Type
- AI, Web
- Role
- Founder / Lead Engineer
- When
- Jul 2026 – present
- Length
- 4 mo so far
- Status
- In progress
- Type
- AI, Web, Platform
The problem
Centralised the customer journey and operational data, reduced manual hand-offs and set up a documented AWS foundation.
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.
Small teams stitch together disconnected tools for websites, customer communication, content, analytics and operations, while generic AI assistants lack safe access to business context and actions.
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.
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.
Pairly gives each business one governed platform where specialised agents can work across those functions. It combines tenant-scoped AI agents, websites and CMS, CRM and communications, newsletters, analytics, integrations and a skills marketplace.
Stack
- Python
- AWS
- Paystack
- Sage
- Zoho
- 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
- Python
- FastAPI
- PostgreSQL
- Redis
- Next.js
- React
- Azure
- LangChain
- Docker
Highlights
- Python APIs and AWS deployment architecture
- Paystack, Sage Accounting, Zoho Bigin and Zoho SalesIQ integrations
- 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
- Tenant-scoped agent runtime with durable memory, model routing, typed tools and permission ceilings
- Streaming agent UX with human approval gates, audit events and token budgets
- Installable skills marketplace with automated validation and human publication review
- End-to-end features spanning API, CMS, renderer, email and PDF output
Infrastructure choices
- AWS
- Vercel serverless (Next.js route handlers)
- Azure OpenAI
- Supabase Postgres + pgvector (HNSW)
- TypeSafe Jev
- Azure Blob Storage
- PostgreSQL
Outcome
Centralised the customer journey and key operational data, reduced manual hand-offs and established a documented AWS foundation for future development.
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.
A broad working platform with multi-tenant permissions, real-time agent execution, publishing and revision workflows, provider integrations and installable skills, with approval gates, audit events and human review for consequential AI actions.