Compare

Fashionly vs Multichoice installer payments vs Ventaw

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

Swipe sideways to compare ›

Fashionly ›

Your style, elevated: an AI stylist that starts with what you own

Multichoice installer payments ›

R5M+ paid to installers in the first six months

Ventaw ›

Secure, isolated environments for developer workloads

At a glance

Role
Founder / Lead Engineer
When
Apr 2026 – present
Length
7 mo so far
Status
MVP
Type
AI, Mobile, Web
Role
Integration engineer
When
Delivered
Length
—
Status
Delivered
Type
Platform
Role
Founder / Lead Engineer
When
In progress
Length
—
Status
In progress
Type
Platform, Web

The problem

Fashion-commerce recommendations usually optimise for another purchase without understanding what the customer already owns.
Integrated the installer management system into Multichoice's payment process so installers are paid accurately and on time.
Environment provisioning, session management and resource monitoring, designed for security, multi-tenancy and concurrent workloads.

What was built

Fashionly grounds recommendations in the user's wardrobe, builds outfits from existing items and recommends products only where a genuine wardrobe gap exists. Khanya, a LangGraph stylist with about 15 typed tools, handles wardrobe access, catalogue search, saved looks and human-stylist bookings.
—
—

Stack

  • Next.js
  • Kotlin
  • Supabase
  • LangGraph
  • MongoDB
  • SSE
  • Payments integration
  • Next.js
  • FastAPI
  • Docker

Highlights

  • Khanya: a LangGraph tool-calling stylist with about 15 typed tools
  • MongoDB-checkpointed conversation memory and SSE streaming of tool progress and grounded product cards
  • Request-scoped Supabase clients with row-level security on every request
  • Processed over R5 million in installer payments within six months
  • Next.js management interface
  • FastAPI orchestration APIs

Infrastructure choices

  • Supabase with RLS
  • MongoDB checkpoints
  • SSE
—
—

Outcome

A working end-to-end MVP across web and Android: wardrobe management, catalogue discovery, conversational styling, saved looks and human-stylist booking.
Over R5 million in installer payments processed within six months.
—

See it