AI - Tech@Hoomanely (Page 3)

Knowledge Base Release Trains: Shipping RAG Content with the Same Discipline as Code

Retrieval-Augmented Generation (RAG) systems rarely fail loudly. They fail in subtler, stranger ways: a support answer sounds different today than yesterday; a troubleshooting step the assistant always got right suddenly drifts; or the bot becomes strangely confident about something no one remembers teaching it. When you dig deeper, the underlying

Choosing the Right Model Architecture for Production

Introduction Choosing the right language model architecture for production is one of the most underrated engineering decisions teams make. Behind every AI feature - from a chatbot response to a search ranking - sits a strategic decision: Should we use an encoder-only model? A decoder-only model? Or a full encoder–

How OCR Quality Shapes RAG Accuracy: A Cloud Comparison

When engineers talk about Retrieval-Augmented Generation (RAG), the conversation often starts at embeddings, chunking, or vector databases. But the uncomfortable truth is this: RAG quality is bottlenecked by OCR quality. If the extracted text is noisy, fragmented, or wrongly segmented, no embedding model - no matter how powerful - can

Policy-Driven Model Routing: Selecting the Right LLM Per Request

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 model, maybe a provider

Designing Audio Anomaly Detection for Pets: A Real‑World Engineering Blueprint

Detecting when something "sounds wrong" during a pet's mealtime seems simple - until you try to engineer it. Background noise, human speech, utensils clinking, bowls moving, fans humming, and wildly different pet eating styles create a dense acoustic jungle. Within this chaos, the goal is to

Product

Dogs don’t speak in symptoms. They speak in patterns.

TLDR: EverBowl captures patterns automatically, and EverWiz explains them in simple language, giving pet parents peace of mind and early clarity long before visible symptoms appear. This article breaks down why single events mislead, why vets care about trends, and how Hoomanely is building a pattern-first health system for pets.

Observation-First AI Infrastructure for LLM-Powered Systems

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

How BERT Learned Pet Questions (And Got Really Good at It)

Introduction: Why We Needed a Question Classifier At Hoomanely, we receive thousands of pet‑related questions across health, behaviour, grooming, food, training and more. These queries help us understand what pet parents care about-and where our product needs to improve. But manually reviewing every question is slow, inconsistent, and impossible

Backpressure for LLMs: Managing Load Spikes and Token Floods in Real-Time AI Services

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 drowning in

From Single‑Point LiDAR to 3D Depth Sensing: Why EverBowl Is Upgrading Its Vision

Introduction In pet‑tech, the difference between “working” and “truly reliable” often comes down to how well your hardware understands the real world. At Hoomanely, we’ve spent months refining EverBowl’s proximity pipeline – the system that helps our smart bowl understand a dog’s face position, maintain safe distances,