AI coding agents are notoriously bad at anything that involves spatial awareness.

Over the weekend I took pictures of the four walls of my office and asked Claude Desktop to examine them and give me a plan for tackling it. It absolutely “understood” my room, identifying the different (messy) workspaces and various piles of stuff on the ground. It generated a checklist with targeted advice and said that I should be motivated to clean up because the “welcome back daddy” sign up on the wall indicates that my kids love me and want a nice space to share with me.

I vibe-code TUI and GUI by making statements like “make the panel on the right side two pixels thinner”.

Related to this thread, I explored agentic looping for 3d models (with a swift library, could be done with this Rust one by following the workflow: https://github.com/ConAcademy/WeaselToonCadova

I've found they are actually quite good at semantic geometry even if they struggle with visual or pixel-based reasoning. Since this is parametric the agent just needs to understand the API and constraints rather than visualize the final output. It seems like a code-first interface is exactly what you want for this.

For that there’s openscad

Breaks down for complex parts with lots of repeated operations, suffers from floating point rounding errors. No constraint solver.

Usually when one needs constraints one can code it up as a recursive function.

That’s certainly not the case for most situations where a constraint solver is useful

Worked for the one time I needed it, and it seems to be a frequently used technique for folks using OpenSCAD.

Curious if something different could be achieved using Python....

I've even already asked an LLM to generate designs in openscad, and there's plenty of examples out there. Obviously there's a complexity limit, but there's also a cheat sheet that makes it pretty easy to discover how to do almost anything that's possible within.