> If anything, I’d expect them to write the weirdo xml of that cursed file format directly.

Isn't this essentially what Claude Cowork is doing? AFAIK, it's running python in a VM and using stuff like xlxswriter, openpyxl, etc. at least it was last time I used it to generate some docs.

I've done that myself too when making some excel reports for management out of pandas data frames.

Microsoft's own different versions of Office can't always reliably read/write docx between them.

Is a layer of LLM going to make this better or worse? Could you train a model to be very good at it?