The honest reason I built Tailways.
I didn't set out to build a dog company. I was building SYLON, which senses a person's state and nudges it toward calm. Dogs were the obvious next question, the animal closest to us, and nobody could tell owners how their dog actually felt when they weren't home.
A friend's dog made it real. He'd fall apart every day she left for work, for hours, and she had no way to know how bad it got. That's when this stopped being an engineering exercise.
We tried heart rate first, and failed. Fur defeats optical sensing, and the moments you most need a reading are the moments the signal is worst. So we changed the question. Instead of a number, an emotional state the owner already understands, sleeping, calm, alert, anxious, active, measured against that dog's own baseline.
We read it with 24GHz radar through the coat, nothing touching skin. There's no published reference for this on dogs, which was the hard part and most of the reason I wanted to do it.
What's proven: twenty-nine hours of continuous recording on a live dog. What isn't: classifier accuracy, which needs independent scoring against video, still in progress. I'd rather tell you that than oversell it.
I'd never had a dog before this. I came to it as an engineer with a loop that worked on humans. I still can't ask a dog how it's doing. But I'm a lot closer to being able to tell.
Shared as personal experience, not a veterinary claim. Tailways is experimental and is not a medical or veterinary device.