AI features that ship
RAG pipelines, MCP servers, and agent workflows wired into real products — not notebooks. Retrieval, tool use, and the guardrails around them.
Full Stack · AI Engineering
I build AI-driven systems on top of production web apps — RAG pipelines, MCP servers, and agent workflows, backed by the APIs and infrastructure that keep them reliable. This is my portfolio and the place where I write down what I learn along the way.
What you'll find here
RAG pipelines, MCP servers, and agent workflows wired into real products — not notebooks. Retrieval, tool use, and the guardrails around them.
The APIs, data, and cloud infrastructure that carry those features — because an AI feature is only as good as the system serving it.
Deep dives on applied AI, architecture, and the failure modes that only show up once real traffic arrives.
Latest writing
A small TypeScript server with one tool, tested with curl before any client touched it, and the three separate reasons Claude could not find it once it was installed.
Read articleThe admin app was sending tokens the API never checked. Closing that without breaking my teammates, opening exactly two endpoints for the MCP server, and moving the API to Azure Functions.
Read articleAlways up for talking architecture, trading war stories, or hearing about an interesting problem.