Atlante
Find the files your AI coding agent is silently bloating. Scans your repo locally and ranks files by size and fan-in, so you know what to refactor before the next session. No LLM, no upload.
Log
Projects I'm building, essays I'm writing.
Projects
What I'm building
Tools, experiments, and things in progress.
TODO add image
gitwell
Make selected agent-written changes explain themselves before they become history. Review the diff, edit the summary, then copy it into your Git client.
daglens
An open-source harness for simulating, inspecting, and stress-testing multi-turn LLM pipelines.
Architect
A system for turning vague software ideas into clearer requirements, decisions, and handoffs before implementation starts.
Writing
Essays and notes
Longer-form pieces about orchestration, architecture, and how LLM systems actually behave when you ship them.
Review the diff before it becomes history
gitwell is a small Rust desktop app for making agent-written changes explain themselves before they become commit history.
Turn code bloat into a refactor queue
A local VS Code plugin that finds the files your AI coding agent keeps bloating, then ranks them into a practical refactor queue. No LLM, no upload, no telemetry.
You Can't Unit Test an LLM Pipeline. Try Chaos Engineering Instead.
Multi-turn AI orchestration fails in ways that no assertion will ever catch. The fix is not better metrics, but chaos engineering for LLM pipelines.
Architect v0.3: tightening the discipline loop
The latest release makes the planning loop stricter, clearer, and much harder to skip when the urge to vibe-code kicks in.
Why Architect stays desktop-first
Keeping the product local changes the trust model, the UX, and the kind of features worth building.
SQLite as the memory layer for a local tool
A small local database is often enough for the kind of continuity an AI-assisted desktop app actually needs.
Writing the build log while the product is still messy
Documenting a product before it feels finished is uncomfortable, but the notes are more valuable when the edges are still visible.