I’m John Young.
I run engineering at Combine Capital and Infrared, and write research-backed essays on running AI coding agents in production — every claim traced to a primary source.
github.com/johnayoung linkedin.com/in/jyoung1985 john.anto.young@gmail.com rss
Ledger
Essays19
Pillars6
Evidence base verified2026-07-13
Recent Essays
- Rank Your Agent Trace Fields by What You Can Never Get Back Production Operations A conformant agent trace proves the run failed and cannot locate where. Rank the fields you write at call time by what no later analysis can recover.
- The Topology You Can Review Is the Topology You Can Run Agent Runtime Eighteen of thirty agents made the same git branch. Default to one agent on coding work, then add an edge only when a named constraint forces it.
- AI Code Review Is a Property of Your Team, Not the Tool Team & Process Two teams ran the same AI reviewer and reported opposite results. Stop importing a verdict from the discourse and run the diagnostic on your own team.
- Stop Picking Your Coding-Agent Model Off a Leaderboard Evals & Verification Your team is about to swap coding-agent models over a two-point leaderboard gap. Anthropic measured six points of movement from infrastructure alone.
- Task Decomposition for AI Coding Agents: Draw the Graph First Task Design Across 20,574 agent sessions, the top failure was violating a stated constraint. Draw the task graph before the prompt: nodes, owned files, and contracts.