A SaaS vendor quoted us $43,000 a year to run speakers for my @AIdotEngineer conferences. That would be fine if it delivered the qualitySo we asked builders to clone it with coding agents, open source, eval by the people who'd actually use it: our human events team.

72 teams submitted. This is what we learned: how the best builders split work between Claude Code and Codex, why our own AI judge ranked the winner 19th, the three things almost every clone got wrong, and why owning software is a different job from building it.