I've been using Blender via Astra (and Sol before they) without any UI automation at all - Blender supports writing and executing Python scripts, here's how I'm doing that: https://til.simonwillison.net/llms/blender-coding-agents-mac...
I'd be surprised if any of the impressive Blender demos doing the rounds at the moment were built by having an agent control the mouse and keyboard against the Blender application.
Interesting, thanks for sharing!
A scripting API makes the problem much more approachable, but what about those videos where Astra is drawing people from a photo? Here's one using canva: https://x.com/iam_zachi/status/2095992132620136677
Is that also using scripting to batch updates? It does look as if the mouse is moving.