openclaw just dropped one of the most important updates.. pretty good jump for my setup honestly.. >discord components my agents can build actual components now.. buttons, dropdowns and modals ... the whole thing.. which makes my whole setup way smoother and more intuitive to use for example, your researcher agent detects 3 new AI tools and shows you a card with each one and a dropdown to pick which agent should investigate etc.. and its fully customizable the cards are cool but you don't have to put everything under them.. the whole point is to not be involved in every step.. just the decisions that actually matter..kinda be wise about what you want to see and what you let your agents handle on their own.. >nested sub-agents this is where it gets crazy.. i've been running sub agents for a while, my agents spawn temporary interns for quick tasks, but interns were always the end of the chain, they would do one thing and report back now they can hire their own interns.. so my agent john got a research task, he spawned 3 interns to investigate in parallel.. one of them hit something deep enough that it spun up its own intern to dig further.. the real win about this is that the agents can follow a rabbit hole on their own without you being a bottleneck.. applied all of this this morning.. good that opwnclaw is focusing on good UX too..