Selected work
Things I've built
Production systems, not demos. A few are internal, so some repos stay private.
MCP servers for Meta Ads & Google Ads
Coming soonModel Context Protocol servers that let an LLM query live ad-account data — campaigns, spend, performance — and return structured, ready-to-analyse insights. Read-only and typed, safe to point at production accounts.
Competitive audit tool
Coming soonScrapes competitor sites and ad libraries, transcribes video creatives with Whisper, and uses Claude to extract structured competitive data — offers, angles, funnels — into a single report.
Google Chat onboarding automation
Coming soonAutomated employee onboarding across Google Workspace: provisions Chat spaces and runs templated welcome flows via GCP service accounts with domain-wide delegation. No manual account setup.
AI Lead Router for Real Estate
In developmentA RAG + agentic workflow that qualifies inbound property leads, matches them against listings with pgvector, and routes each one to the right agent with a drafted first reply.
Stack
Tools I work with
A short list I actually reach for, grouped by where it sits.
-
AI / ML
Claude API MCP RAG · pgvector Structured outputs LangChain (learning) -
Backend
TypeScript Node.js Python Supabase PostgreSQL -
Automation
n8n (self-hosted) Google APIs Meta APIs -
Frontend
Next.js Astro Tailwind -
Infra
Vercel Docker Caddy
Day-to-day I build with coding agents like Hermes Bot and Openclaw to move faster.
About
Short version
I moved from paid media to building AI systems in about a year — self-taught, by shipping.
My focus is production over prototypes: systems that run every day, fail loudly, and are cheap to keep alive. I care more about a workflow that quietly saves hours than a demo that impresses for five minutes.
Contact
Get in touch
Best over email — I read everything and reply personally.