“The large language models represent what would traditionally be considered compute. Then you have these agentic harnesses, like Claude Code or Claude Cowork, that sit at the layer that would have been occupied by the operating system, orchestrating the compute across tasks. And then plugins, skills and MCP servers occupy the app layer. It's why more of the value is accruing to the harness and plug-in app layer: once you get that part right, you can start doing model routing and pick the right compute for the right task.”

a good question. I mean, I think the thing that I'm seeing sort of start to play out is I think the way software sort of works for certain personas is changing pretty drastically. I think you kind of have a pattern emerging where, you know, the large language models kind of represent what would traditionally be considered compute. They're the reasoning and computational layer. And then you have these agentic AI harnesses, you know, like a Cloud Code or Cloud Co-Work, ChatGPT work, you know, news, dots, all of these things that sort of sit at this layer that would have traditionally been occupied, I think, by the operating system. This is sort of the iOS or Windows sort of layer where you're orchestrating the compute across different tasks. And then you have sort of the plugins, skills, MCP servers, which I think occupy the area in the stack that really would have been the app layer, right? So it's like these are the different applications and extensions that you can plug into the operating system that do, you know, domain-specific work, are opinionated about how certain things are done. And so as I think about that architecture, I think really deeply about how we help, you know, people that are trying to build something in that world explore the things that they need across the different layers of that…