Skip to content

About

I've always been drawn to the how behind data — how it's architected, engineered, and ultimately put to work. These days that curiosity is pointed at AI systems end to end: the pipelines that feed them, the models wired into products as real features, and the interface layer people actually touch.

This site is proof of that work as much as a description of it — it runs on the infrastructure: a Postgres-backed content system, a RAG chat widget grounded in what's actually published here, a public MCP server, and a handful of scoped agents that write to it directly.The build log has the real story behind each piece, mistakes included.

If you're navigating the AI-data terrain too — whether you're standing up your first pipeline or deep in the weeds of an existing one — I'd love to help however I can.

What I do

Data pipelines

Ingestion, transformation, and orchestration that hold up under real production load — the unglamorous plumbing that decides whether anything built on top of it can be trusted.

A dbt Semantic Layer Over My Own GitHub Activity

AI integration

Wiring Claude and other models into products as features, not demos — tool use, structured output, and small agents scoped to one job, each held to the same audit trail as a human editor.

An Agent Toolkit for Running the Site

Applied AI features

The interface layer on top — the part your users and customers actually touch. Grounded in what's actually published, cited, and honest about what it doesn't know.

Retrieval-Augmented Chat: Ask This Site a Question

Skills & tools

  • Data Engineering & Warehousing
  • Big Data & Pipelines
  • Multi-Cloud Platforms
  • LLM & AI Integration
  • AI Orchestration & Observability
  • Retrieval & Vector Search
  • Business Intelligence & Analytics
  • Machine Learning
  • Application & Cloud Engineering