Most conversations about Retrieval-Augmented Generation start with embeddings, chunking, or which vector database to use. That's the wrong starting point. If the text coming out of your OCR step is noisy or split in the wrong places, no embedding model can put the meaning back together. RAG quality
The first LLM integration is usually simple: you pick one provider, one model, one API key, and ship. The second and third are where things start to hurt. Suddenly you have a "cheap" model for bulk tasks, a "smart" model for critical flows, maybe a vision
Knowing when a pet's mealtime "sounds wrong" seems like an easy problem, until you actually try to build it. Kitchens and living rooms are loud: background noise, human speech, clinking utensils, bowls sliding across the floor, humming fans, and every pet has its own eating style.
Short version: EverBowl captures behavioral patterns automatically, and EverWiz explains them in plain language, giving pet parents earlier clarity, often well before any visible symptom shows up. This post covers why single events are misleading, why vets actually care about trends, and how we're building a pattern-first health
When an AI feature behaves well, it feels effortless: the user asks a question, the model replies, and everything just works. But under that smooth surface, LLM calls are some of the most complex operations in your stack, huge prompts, variable latency, opaque provider behavior, and costs that can drift
Why we needed a question classifier At Hoomanely, pet parents send us thousands of questions covering health, behavior, grooming, food, and training. Those questions tell us what people actually care about and where the product falls short, but reading every one by hand is slow, inconsistent, and doesn't
LLM features usually start life in a happy place: a handful of users, low traffic, and plenty of quota. Latency looks fine, tokens are cheap, logs are quiet. Then a product launch, a marketing campaign, or a new "Ask AI" button lands, and suddenly your once-stable service is
Introduction In pet tech, the gap between something that works and something that's actually reliable usually comes down to how well the hardware reads the real world. At Hoomanely, we've spent months refining EverBowl's proximity pipeline, the system that helps our smart bowl track
Introduction Most modern applications, from image similarity to RAG systems, depend on fast vector search. Once you embed text, audio, or images into high-dimensional vectors, finding the closest matches turns into an approximate nearest neighbor problem, and that's where vector databases like FAISS, Milvus, Pinecone, Weaviate, and Elasticsearch
Modern AI products feel personal only when they remember, that bug you were debugging yesterday, the pet profile you set up last month, the long-running coaching thread you keep coming back to. Under the hood, though, LLM inference APIs don't remember anything. Every call is a clean slate,