I think solutions like Plasmic, Refine, and React-Admin probably have a strong place in this AI future. They combine being able to work LLM-first while still offering agility by providing a solid foundation to build on. Otherwise you're stuck to the whims of untested AI slop for everything from security to component design. There's a reason people writing AI code still use libraries and it's the same reason we used libraries pre-AI. They're tested, they're stable, they have clear documentation. Just because the cost of code is zero doesn't mean the cost of software systems is zero.