#ai-agents

Articles tagged with #ai-agents

How I evaluate AI coding agents: the rubric taxonomy
If you ship an AI coding agent into a team's workflow, "did this output look right?" is not enough. You need rubrics: scorable properties that say what good and bad mean before you grade anything. I k
Jun 6, 20263 min read17
What model checking taught me about evaluating AI coding agents
Why a unit test is the wrong tool for a nondeterministic agent.
May 25, 20263 min read10
Three things that don't port between Claude Code, Codex, and Windsurf
Claude Code, Codex, and Windsurf now look alike: all three have skills, hooks, and plugins. So it's natural to assume your setup ports between them. It mostly doesn't. I maintain a repo that targets a
May 23, 20263 min read

#ai-agents - Alex Voloshin — Agentic-dev tooling, evals & tri-vendor parity