AWS just shipped an experimental library through strands-labs, AI Functions, which execute LLM-generated code at runtime and return native Python objects. They use automated post-conditions to verify outputs continuously. Unlike generate-and-verify approaches, the AI-generated code runs directly in your application.
I've been testing Kiro for a few months, and yes, it's an agentic IDE like many others. However, a lot of the features are different - the spec driven development is a game changer. It feels like you're truly software engineering versus vibing - you break a problem into small, solvable steps using specs. So are agent hooks - there are great use cases like updating Asana statuses or syncing your design system with Figma.