Back to home

Projects

Every system I've built and run.

A mix of automations, data platforms, and production software. Here's what each one does, and what it changed.

Multi-Platform Content Automation Pipeline

Project · Content automation

Multi-Platform Content Automation Pipeline

One draft goes in. A finished article, a set of branded assets, and a scheduled week of platform-native posts come out — published to the blog and across Instagram, LinkedIn, and Pinterest, hands-off after a single approval.

1 → 50+
One draft, 50+ posts
4
Platforms, one run
1 approval
Then it runs itself
Claude Gemini Astro Zernio Multi-platform Python
Learn more
Reusable Vision & Image Skill for Claude Code

Project · Agent tooling

Reusable Vision & Image Skill for Claude Code

Claude Code can read images and sketch visuals, but only so far — Gemini's vision and image generation go well past it. I built one Gemini-backed skill that puts see and draw behind a single command — a reusable gateway every project, agent, and skill builds on.

2
See & draw, on tap
1
Gateway, one API key
Reused
Across every project
Claude Code skill Gemini API Python CLI Agent tooling
Learn more
Studio-Grade AI Product Photography Pipeline

Project · AI product photography

Studio-Grade AI Product Photography Pipeline

A few phone photos of a garment go in. A full set of studio-grade shots comes out — flat-lays, on-model, detail crops — in minutes, checked against the real product.

~90%
Lower cost per shot
Days → min
Per-product turnaround
10+
Shots per product
Gemini Vision + image gen Python Validation loop
Learn more
Multi-Tenant Gym Management Platform

Product · Gym management SaaS

Multi-Tenant Gym Management Platform

A complete gym-management SaaS — members, billing, inventory, payroll, and analytics — built as three apps over one FastAPI service, multi-tenant and trilingual, shipped to production through CI/CD.

8 modules
Members to payroll
3 services
Front · admin · API
FR·EN·AR
Multilingual + RTL
React FastAPI PostgreSQL Docker / CI-CD Multi-tenant i18n + RTL
Learn more
Production-Grade Document RAG Backend

Project · RAG backend

Production-Grade Document RAG Backend

The backend for a document-QA assistant: upload PDFs, ask in plain language, get cited answers. An async RAG pipeline — OCR, hybrid retrieval, reranking, generation — spread across worker pools, fully observable, and not locked to any one AI vendor.

3
Isolated worker pools
30 → 10
Retrieved, reranked to the model
2-stage
Reranking — MMR + LLM grading
RAG FastAPI Celery Weaviate PostgreSQL Observability Python
Learn more
Postgres Partitioning for 95% Faster Queries

R&D · Postgres optimization

Postgres Partitioning for 95% Faster Queries

Two large Postgres databases with drifted schemas, merged into one through a reversible, idempotent load — then the 56-million-row table declaratively partitioned and benchmarked to at least 95% faster on the filters that matter.

≥95%
Faster on filtered queries
56M rows
Two databases merged into one
2-level
Declarative partitioning — list × range
PostgreSQL Partitioning ETL / migration Benchmarking Data integrity Python
Learn more
Agent-Ready Brand Consistency Skills

Project · Brand systems

Agent-Ready Brand Consistency Skills

Two skills that pin a project's visual identity and voice into a DESIGN.md and a VOICE.md — machine-readable files every agent loads and self-checks against. Author the brand once; stop re-briefing Claude every session.

2 files
DESIGN.md + VOICE.md
Author once
Every agent reads the same spec
Self-check
Conform before shipping, no re-brief
Claude Code skill Agent tooling Brand systems Design tokens Voice / tone Automation
Learn more

Have a process like these?

Tell me what you're working on, and I'll come back with whether I can help and what a first step looks like.

Get in touch