This is a great lens into agent behavior--particularly Claude Code in this case, but it raises a governance question: when agents autonomously choose tools that have cost implications (paid APIs, cloud resources, licensed software), who's enforcing the budget in a world where agents actually have autonomy to spend real money? Tool selection isn't just a technical preference "problem" — it's a spending authorization problem. The agent picks the "best" tool, but best for whom and at what cost and how is "best" really determined and verified?
No comments yet.