Human-in-the-loop can improve AI safety, but it usually does not by default. Putting a person behind an approval button only helps when the consequence is high and that person can realistically catch the mistake in time. When they can't, the approval click is a rubber stamp that adds latency, manufactures a false sense of safety, and sets the human up to take the blame for a failure they were never positioned to prevent.
This article unpacks when human oversight of AI genuinely raises safety, when it only looks like it does, and what real AI safety for agents requires instead.
The wrong question, and the right one
Most discussions of human in the loop AI safety start with "should a human review this?" That question is nearly useless, because the honest answer is almost always "sure, why not." The better question is sharper and uncomfortable: can a human realistically catch this mistake in time?
If the answer is no, then a review step is theater rather than a safety control. The agent still does the wrong thing, and you have simply added a person whose name is on the approval. The framework reframes oversight around this distinction, and it changes nearly every design decision that follows.
