Human in the loop is not a robot safety specification, and ADAS already proved it
Human-in-the-loop as a yes/no rule carries no engineering content. Specify takeover latency, teleop ratio and robots per operator instead.
ADAS
Eval as spec: grade the agent's side effects, not its success story
Judge agents by executable end state and pass^N, not self-reports; the eval harness is the product spec, and verification depth is the constraint.