Models, pipelines, and edge inference — how we design and ship AI systems that hold up in production.
An edge AI camera runs its vision models on the device that holds the lens, instead of streaming video to a server. A proximity trigger decides when to capture, a quality gate rejects frames that are too dark or too blurry in under a millisecond, and only frames that pass
Pet facial recognition identifies an individual dog, not a breed, by measuring the geometry of its face and comparing that measurement against a stored profile. In our bowl-mounted camera system, a frame passes through seven preprocessing steps, a 46-point landmark model aligns the face, an embedding model turns the aligned
"Why is Max scratching more this week?" Somewhere in Max's data, the makings of an answer exist: his bowl logged a food switch on July 5, the new kibble's ingredient list includes chicken meal, his tracker has flagged more nighttime restlessness since July 8,
Three different sources have something to say about Max's appetite this month. His smart bowl has logged five smaller-than-usual breakfasts. A vet note mentions "monitor appetite." A dog-care book says goldens often eat less in summer heat. Do we know Max's appetite has dropped?
A smart bowl reading looks like this: 120 g served, 82 g eaten, 340 seconds, 7:14 a.m. It is perfectly precise and almost meaningless on its own. A vet note is the opposite: rich with meaning ("mild tartar, monitor appetite"), structured not at all. To answer
Our IMU bark classifier now has 11 training generations behind it. This post covers what changed between v8 (our last reported state) and v11 (live as of August 5), introduces a real ambient audio clip where the audio classifier was completely fooled but the IMU was not, and explains the
Every RAG tutorial follows almost the same flow: convert the user's query into an embedding, retrieve the Top-K most similar documents, and pass them to the LLM. The part that's usually skipped is a simple question: Why K? Why retrieve 3 documents instead of 1? Why
In the first post in this series we described a rule-based sleep detector for our collar wearable: bucket the IMU stream into one-minute epochs, score each epoch by how much the acceleration is changing, and call a long enough run of quiet minutes a sleep bout. We ended that post
At 7:14 this morning, a smart feeding bowl logged something small: Max, a six-year-old golden retriever, left a third of his breakfast. His collar tracker says yesterday's walk was completely normal. A vet note from two weeks ago mentions mild tartar buildup. And a dog-nutrition book on
In our previous post we built the first version of an ML bark classifier: 28 features extracted from collar IMU windows, a RandomForest winning a model bakeoff, bark F1 of 0.714 on a held-out test set. That number looked good. It was wrong. The Number That Was Lying to