Models, pipelines, and edge inference — how we design and ship AI systems that hold up in production.
Search is usually treated as a solved problem. Store the data, index the field you plan to query on, look it up. That holds up perfectly well right until the moment the words someone actually types don't match the words you indexed. The moment exact-match search quietly fails
Our IMU-based activity tracker clips to a dog's collar and, in principle, can tell you how far your dog walked today. In practice it needs a teacher. An accelerometer strapped to a moving neck produces a beautiful, noisy waltz of a signal, and turning that waltz into a
The last post ended on an open problem: we could not make phone-photo galleries work well enough to matter. Adding more enrollment images made things worse, not better. This post is about what we changed and what finally moved the numbers. The setup Before getting into results, it helps to
In our previous post we hit around 92% identification accuracy on detected frames. That result came with a catch we had quietly set aside: the gallery was built from bowl camera images, evaluated against bowl camera images. What happens when that changes? The Problem With the Current Setup A quick
Our smart bowl fires its camera whenever anything comes within 40 centimetres — a dog's nose, a human's ankle, a broom. That is by design: in the data-collection phase, every visitor is a labeled training sample. But the product question is sharper than the trigger: the bowl
Everbowl logs a dog's day in numbers. Load-cell weights on every bowl visit, water refills, eye-temperature frames from the thermal camera, ambient temperature and humidity, audio classifications of chewing and licking. Across a fleet this runs into thousands of events per dog per day. Almost none of it
A dog cannot tell you it slept badly. It just does, and then it is cranky, or slow on the morning walk, or off its food, and you are left guessing why. Sleep quality turns out to be one of the earlier signals that something is wrong with a dog:
In our previous post we described the multi-stage vision pipeline we built to identify dogs by their facial landmarks - covering preprocessing, embedding model training, gallery building, and real-time inference. This post covers what happened when we ran it on real camera footage and reviewed every result manually. Setup A
When you're building a thermal-detection system to watch over a dog, the sensor you pick is only half the story. The lens sitting in front of it — and specifically how wide it sees — quietly decides how far away you can read your pup and how forgiving the aim
In our first post on the bark detection pipeline, we showed how a single threshold on jerk_3d_max gives a useful signal for detecting barks from a dog collar IMU. For any capture window where jerk_3d_max crosses 6.5 g/s, the rule calls it a bark.