Work

Two halves of one platform

I build and operate a production knowledge platform. The most useful way to read these is as one system: a library people use, and the pipeline that fills it.

Flagship · Search & knowledge platform01

Shia LibraryLive

A production digital library: diacritic-insensitive Arabic search, English full-text search, and semantic vector search over tens of thousands of passages — with row-level access control, an in-app CMS, and a reading experience tuned for dense scholarly text.

Next.js 15React 19Supabase / PostgrespgvectorOpenAI embeddingsMUI

~66k: passages indexed
~11.7k: static pages
3-layer: caching + RLS
Live: shialibrary.com

Read case study

Data engineering & LLM orchestration02

Usul PipelineLive

A resilient, cost-optimized ingestion + LLM-translation pipeline that turns scattered source texts into a clean, structured corpus.

Pythonasyncio / httpxClaude (Anthropic)Supabase / PostgresPrompt caching

220: books processed
35k+: passages translated

Case study

On the roadmap

What I'm building next

These aren't shipped yet — listed honestly. The first items deepen the platform; alongside them I'm branching into independent tools that solve broader problems. Depth and range, not scattered demos.

Deepen the platform: citation-grounded RAG with inline, verifiable provenance, plus a retrieval eval harness so quality is measured, not assumed.
A single explicit hybrid ranker (keyword + vector + reranking) replacing the two separate search paths.
Branch out: an open-source LLM gateway (provider routing, caching, cost observability) — useful to any AI app, not just mine.
More broadly — distributed-systems and real-user products in new domains, to build range beyond a single platform.

See experiments →