Feels a bit like an extension of having an LLM make a JSON file for text/numbers/dimensions in an image, allowing one to edit it, then use it as a reference when a prompt re-works it --- just one has to find the right node to update/edit.

Those stairs look challenging to say the least

We need to find a way of coming up with better names for software.

Rhino is unusually suitable for AI agentic generation since it is very command line driven and there are a lot of example RhinoScript projects. McNeel, the Rhino developers, also have a lot of open source stuff, Rhino MCP, and explicit support for headless Rhino [1], which makes it even more amenable.

[1] https://github.com/mcneel

There's also Raven which is an AI tool built on top of Rhino3D.

https://www.raven.build/ https://www.youtube.com/@RavenCAD/videos