Systems engineer · AI tooling · Privacy-first products

I build reliable agent systems and the software around them.

Systems engineer building agent runtimes, privacy-first applications, and production AI tooling.

Rust, Python, TypeScript, Cloudflare, SQLite, and MCP. I care about measurable behavior, safe defaults, and small systems that are easy to reason about.

01 / Principles

Privacy-first architecture.
Exacting precision.
Local retrieval.
001

Make the important path obvious. Reduce surface area before adding features.

002

Treat privacy, account boundaries, and operational evidence as product requirements.

003

Build agent systems as composable protocols, not opaque demos.

02 / Selected Work

Crafted Systems.

Interactive guides

More like a technical workbench than a post archive.

Focused labs with runnable examples, validation notes, and concrete tradeoffs. Less essay archive, more technical interview workbench.

guide-workbench.ts
type GuideLab = {
  goal: "senior-engineer ramp-up";
  includes: ["mental model", "pitfalls", "checks"];
  output: "interview-ready understanding";
};

run(lab).verify().ship();

04 / About

The Workshop.

I build agent runtimes, privacy-first applications, and production AI tooling. My work sits between systems engineering and product delivery: tool loops, retrieval, encrypted storage, CI, and deployable user interfaces.

I am strongest where architecture needs to become working software. I like small protocols, clear boundaries, local-first data, and validation that proves the system behaves as intended.

Core stack

Rust, Python, TypeScript, Cloudflare Workers, Next.js, SQLite, Prisma, MCP, A2A.

Technical snapshot

Languages
Rust, Python, TypeScript
Systems
MCP, A2A, Workers, SQLite FTS5
Product
Next.js, Prisma, OAuth, CI/CD