Projects

Security research for AI agent harnesses and teams, focused on safer and more reliable agent orchestration.

A zero-trust security layer that sits between RAG pipelines and sensitive data sources.

Opinionated project templates with built-in guardrails so AI coding agents produce reliable, maintainable code from the start.

A lightweight spec-driven workflow for AI coding agents: explore an idea, propose a chunked change, apply one slice, then fold the result back into living specs.

One deterministic Python quality loop for linting, typechecking, tests, coverage, and agent-authored pull requests.

Curated security and privacy recommendations for teams that need practical guidance they can actually follow.