I believe they mean aggressive delegation to minimize context bloat in the coordinating agent.
This is a really useful technique in my experience. The harnesses are starting to do it more on their own but if you encourage the use of more subagents, I find it's typically nothing but win.
that would make more sense, trimming context with subagents sounds like an overkill
This is a really useful technique in my experience. The harnesses are starting to do it more on their own but if you encourage the use of more subagents, I find it's typically nothing but win.