Compare

Pairly vs Fashionly 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: AI, Web
  • Order: CaseNotes (Feb 2026 – present) → Fashionly (Apr 2026 – present) → Pairly (Jul 2026 – present)

Swipe sideways to compare ›

Pairly ›

An AI-native operating system for founder-led teams

Fashionly ›

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

CaseNotes ›

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

At a glance

Role
Founder / Lead Engineer
When
Jul 2026 – present
Length
4 mo so far
Status
In progress
Type
AI, Web, Platform
Role
Founder / Lead Engineer
When
Apr 2026 – present
Length
7 mo so far
Status
MVP
Type
AI, Mobile, Web
Role
Founder / Lead Engineer
When
Feb 2026 – present
Length
9 mo so far
Status
Live
Type
AI, Web, Mobile

The problem

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.
Fashion-commerce recommendations usually optimise for another purchase without understanding what the customer already owns.
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

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.
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.
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

  • Python
  • FastAPI
  • PostgreSQL
  • Redis
  • Next.js
  • React
  • Azure
  • LangChain
  • Docker
  • Next.js
  • Kotlin
  • Supabase
  • LangGraph
  • MongoDB
  • SSE
  • Next.js
  • FastAPI
  • PostgreSQL
  • pgvector
  • Neo4j
  • Redis/ARQ
  • Azure OpenAI
  • LangChain
  • LangGraph

Highlights

  • 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
  • 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
  • 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

  • PostgreSQL
  • Supabase with RLS
  • MongoDB checkpoints
  • SSE
  • pgvector + Neo4j
  • Redis / ARQ workers
  • LangGraph with PostgreSQL checkpoints

Outcome

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.
A working end-to-end MVP across web and Android: wardrobe management, catalogue discovery, conversational styling, saved looks and human-stylist booking.
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