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
Essays25
Pillars6
Evidence base verified2026-09-07
Recent Essays
- Agent Tool Design Belongs in Your Harness Audit, Not Prompt Tips Agent Runtime Agents that sent the same write twice reported success 90% of the time. The fix was one tool parameter. Audit what a tool call means, not just whether it runs.
- Diff Review Can’t See Your Agent Regress. A Standing Suite Can. Evals & Verification Per-diff review checks one PR, not whether your coding agent still works. How to run AI agent regression testing as a standing eval suite: triggers, tiers, owners.
- Your Agent’s “Done” Is a Self-Report. Make It a Predicate. Task Design Acceptance criteria for AI coding agents fail when done is prose the agent grades itself. Write end-state predicates a checker runs where the agent can’t write.
- Where a Decision Model Belongs: Placing Jev in Your Stack Architecture Decisions Jev’s launch numbers answer a question you don’t have. The tier it joins already ships at Anthropic, Meta and OpenAI, with the costs published.
- Coordination Is an Architecture Layer, Not a Prompt Instruction Architecture Decisions When a multi-agent pilot breaks, the postmortem blames the model. The failure data says coordination logic buried in each agent’s prompt is the real defect.