I'm Alex Voloshin. I help engineering teams operationalize AI coding agents. This blog is the long-form companion to ai-skills — a public repo of 26 agents, 77 skills, 48 eval rubrics with 288 calibration samples, 18 hooks, 12 rules, and 32 user-invocable workflows that work across Claude Code, Codex, and Windsurf. What you'll find here: - Tri-vendor parity write-ups. Engineering teams adopting AI coding agents shouldn't have to lock into one runtime to get production-grade tooling. Posts here track concrete differences between Claude Code, Codex, and Windsurf, and the patterns that survive across all three. - Eval methodology. Most public discourse on AI coding-agent evaluation is hand-wavy. I write about specific rubrics, calibration sample design, and the failure modes calibration data catches in production. - Formal-methods × agentic dev. LTL, model checking, and formal requirements review apply to agent specifications more directly than people think. Posts at the intersection of academic CS and practical agent orchestration. - Production war stories. Concrete failure modes, post-mortem-style write-ups, and the patterns that grew out of fixing them. What you won't find here: - Generic "AI is changing everything" takes - Tutorials for first-time agent users (better resources exist for that) - Vendor-locked content disguised as agnostic advice 17+ years building production software. Subscribe below if you want one well-edited post per ~2 weeks. No spam, no growth-hack frequency.