doesn’t forcing your agent to think in ruby put it at huge disadvantage though? since the language isn’t that popular it can’t have learned it as well as say python or Java?

Python does have a bigger pool of examples, but agents usually get tripped up by missing context about specific frameworks more than by language syntax. The real obstacle for LLMs is understanding Rails' implicit conventions and magic, not the Ruby language itself.

Claude munches through Ruby just fine, all day long.

The frontier models all handle Ruby just fine. So does th cheap Chinese models like Mini, Qwen, Deepseek.