The question is whether the agent can run the thing it just built, look at the result, and decide whether it actually worked. We gave Kilo the ability to test our own VS Code extension and CLI end-to-end, so it drives the product and observes what actually happens rather than describing what should. When an engineer builds a feature there, the agent usually just spins up a Chrome window and exercises it. Self-testing lets the agent decide what to check now, for the change it’s making, and then actually go check it. That’s the version of Kilo Speed we’re actually chasing: a tighter loop between intent and a working, verified result.