Writing

ChatbotX is an open-source, AI-first chat platform built on a stack close to mine. I checked whether it should replace Chatwoot as the human inbox behind Loma's WhatsApp agent. It shouldn't, and the reason is architectural, not a feature checklist.

Two pull requests against Mastra, two confident Major findings from CodeRabbit. The first was wrong. The second was right, and its proposed fix would have hung the suite. Nothing in the comments told them apart — only running the tests did.

For months our WhatsApp sales agent answered customers on a model nobody had ever benchmarked. When I finally tested that slot against ten alternatives it came fifth — and my own harness lied to me four times on the way to finding out.

A proactive follow-up told a customer their payment link was on the way. No order existed and no link existed. What that incident changed about how I let model output reach people.

Closed-loop self-improvement may be impossible for models trained mostly on their own outputs. That is a boundary condition, not the end of AI progress.