§ Projects
Things I’ve built.
A short, opinionated list. Production systems, evals, and tools — not demos. Selection bias: things I’d still defend a year later.
- 01
Supervisor — a runtime for production LLM agents
A two-tier planner/executor architecture for agentic systems, with first-class plans, replay, and step-level observability.
TypeScript / Node.js / Postgres / Anthropic API
2026
Lead engineer & technical author
Read more →
- 02
Groundtruth — eval harness for retrieval pipelines
A reproducible eval harness for RAG systems: golden questions, citation-level scoring, and regression detection between model and index changes.
Python / DuckDB / Anthropic API / OpenAI API
2025
Solo build
Read more →
- 03
Field Notes — a writing tool for technical practitioners
A markdown-first writing app that turns scattered engineering notes into structured drafts, with model-assisted outline extraction and tone preservation.
Next.js / Tauri / SQLite / Anthropic API
2025
Co-founder & maker
Read more →