Unless it's super straight-forward, it generally works better for me to have the option to edit the instruction so I pass that into an issue that I can edit before assigning. I do often do subtask decomposition instructions though - it doesn't all have to be hitl within a consistent task. Context matters then though, so I try to define my tasks so that context stays under 100k tokens.

optimism

the real gains ought come from looking at where tool calls fail and then (a) improve the tool and (b) improve the instruction.

I saw something that framed this as inner-loop / outer-loop and how subagents are increasingly a better way to prevent context pollution

Evolving harnesses versus static ones

> the real gains ought come from looking at where tool calls fail and then (a) improve the tool and (b) improve the instruction.

I saw something that framed this as inner-loop / outer-loop and how subagents are increasingly a better way to prevent context pollution