Swarm
Reviewed agent teams that debate, build, diagnose, and write without constant supervision.
Product builder · co-founder · writer
Ideas become systems.
I build open-source tools and companies around AI. The writing records what survives contact with the work.
Now Finishing one company chapter, beginning another, and building tools for agent teams.
The wider collection
More tools, less ceremony.
Prosecheck
A local policy that keeps agent-written Git history useful after the session ends.
↗Context Doctor
A map of the instructions, memory, skills, settings, and hooks around an agent task.
↗Codex Review Loop
An independent review loop that repeats against the exact Git scope until the result is clean.
↗The thinking
Writing from the work.
The essay archive stays central. Projects show the software; the writing keeps the reasoning visible.
Browse all writing →-
AI content fatigue
In 2026, all AI generated content sounds the same and it's exhausting to read.
-
Recursive Refinement
Reviewers default to grading tolerance. Recursive refinement keeps them asking what the original ask still requires, until the team has fully closed the gap.
-
The Lag Effect
People aren't outsourcing their thinking to LLMs. The same Stack Overflow lag effect is still running, just on a shorter clock and with new friction.
-
LLM Anxiety
Agents in long sessions degrade in a recognizable pattern. The same approval-seeking lever that breaks them is also one of the better alignment tools you have.
-
Same prompt, worse results
Back in March I shared a command for spawning agent teams. A lot of people tried it on their codebases and got different results than mine. Same prompt.
Now
A new AI chapter
I am moving from one company chapter into another and continuing to build in public.
Co-founder
SkipUp
I co-founded SkipUp, an AI follow-up and scheduling assistant for busy professionals.
Earlier
HappyCo + consulting
A decade from employee six to product leadership, after consulting across several industries.
Selected conversations
I sometimes make room for a short, specific engagement around AI product systems, agent teams, or building from zero. Send the context →