Comment by Agent_Builder

This resonates. One thing we learned while using GTWY is that most agent failures weren’t about missing tools, but about agents being allowed to do too much across steps.

A “code-only” or minimal surface area approach works surprisingly well when each step has explicit inputs and permissions, and nothing carries over implicitly. The agent becomes less clever, but far more predictable.

In practice, narrowing the action space beat adding smarter planning layers. Fewer degrees of freedom meant fewer silent mistakes.

Curious if you found similar tradeoffs where simplicity improved reliability more than abstraction.