“Human in the loop” has become one of those phrases that can mean almost anything, which is another way of saying it risks meaning nothing. A tool can technically keep a person in the loop while making it impractical for them to do anything but click approve. We think the phrase only earns its keep if the human is genuinely able to understand, question, and override what the tool proposes — not just nominally present, but actually in control.

That has consequences for how a tool is built. An output that cannot be examined cannot be meaningfully reviewed, so our outputs are deterministic and logged: the same input gives the same result, and every step can be retraced afterward. A finding that arrives with no way to see why it appeared invites either blind acceptance or blanket distrust, and neither is safe. Being able to look back is what makes staying in the loop a real choice rather than a formality.

It also shapes how a result is framed. A suggestion dressed up as a verdict quietly shifts responsibility away from the person who should hold it. So we are careful to present support as support — never as a decision, never as something that has already been settled. The clinician reads, weighs, and decides; the tool makes that easier, not automatic.

The honest version of “in the loop” is more demanding than the marketing version, and that is the point. A clinician is accountable for the decisions they make. A tool that wants to help them should make that accountability easier to carry, not harder — and it should never, even by accident, take the decision out of their hands.