novarii_

check this out https://strandsagents.com/blog/strands-box-the-big-picture/

> using the harness + model made by the same lab, has vastly better experience compared to more "general purpose" (for the lack of a better term) harnesses

not really, there was a recent benchmark with claude and codex and it showed no difference in ability with a harness like pi agent compared to their native harnesses, pi was in fact cheaper per task.