All that agent behavior will also inform the system, right? So like, yeah, if you put it live and like agents are forever going wrong, right, wrong, right,. All that feeds back in and then it gets better. And then, and then very quickly the system converges on all the right answers. Yeah. We certainly could build a system that does all of those things. Like GPT 3.5 won't negatively do it. I could decide to build on it as a building block. It's capability is very good, but it's not the only generous model in town. But whatever we build on and we're getting really into the room, potentially we would build