Software
The Signals Pets Never Verbalize A dog developing a low-grade fever will not announce it. A dog beginning to experience dental discomfort won't either. Companion animals are evolutionarily conditioned to mask weakness a survival behavior that long predates domestication. By the time a pet parent notices that a
AI
At Hoomanely, a lot of our intelligence runs on models we trained in PyTorch: YOLO segmentation networks that understand what is happening in a frame, a MobileNetV3 classifier that recognises bowls, and a YAMNet-based audio model that listens for specific sounds. Training these in Python is comfortable. Shipping them is
AI
Every Everbowl device sits in someone's home. It watches a dog eat, drink, move, and breathe — tracking feeding patterns, drinking patterns, eye temperature, and ambient sound to keep a quiet, continuous check on the pet's health. It is expected to run reliably for years, update silently
Firmware
In the high-stakes world of embedded firmware development, "optimization" is usually the golden word. We optimize for speed, for power consumption, and perhaps most frantically, for memory. We count bytes like misers counting pennies, shaving off struct padding and squashing enums into uint8_t wherever possible. We analyze
Hardware
A sensor board that is accurate at 25°C on a clean bench is not a finished product. It is a starting point. The moment that board ships inside a real device, it stops living at 25°C. It sits next to a regulator that warms under load. It is
Firmware
The build failed at 11 PM on a Thursday. Not from our code — from a missing pkg-config path. The CMake configure step for Mosquitto was resolving openssl.pc from /usr/lib/x86_64-linux-gnu instead of from the target sysroot. We'd seen this class of error before. Fix it,
Firmware
A customer's home hub stops sending data to the cloud. Logs go quiet. The Linux side looks fine — the bridge service is alive, the CAN driver is alive, but the wireless SoC it talks to over USB-CDC is silent. The chip enumerates as a serial device, so the
AI
When teams build their first Retrieval-Augmented Generation (RAG) chatbot, most of the engineering effort goes into chunking, embeddings, and vector search. That is exactly where we started at Hoomanely. But after months of iterating on a pet-health assistant grounded in veterinary books, nutrition manuals, and clinical PDFs, we hit a
Hardware
Designing hardware for a single feature turning on is relatively easy. Designing hardware for multiple subsystems waking up together without destabilising the system is where real embedded power architecture begins. Most embedded products today are no longer simple MCU boards with a few peripherals. A modern edge device may contain
Technology, Insights and Ideas.
Hardware
Modern embedded products are no longer single-purpose machines. A connected edge device may capture images, process sensor data, communicate over wireless or wired interfaces, store logs, run OTA updates, manage power states, control LEDs, detect proximity, and coordinate with other boards — all inside one compact system. Each feature may be
Software
The Signals Pets Never Verbalize A dog developing a low-grade fever will not announce it. A dog beginning to experience dental discomfort won't either. Companion animals are evolutionarily conditioned to mask weakness a survival behavior that long predates domestication. By the time a pet parent notices that a
AI
At Hoomanely, a lot of our intelligence runs on models we trained in PyTorch: YOLO segmentation networks that understand what is happening in a frame, a MobileNetV3 classifier that recognises bowls, and a YAMNet-based audio model that listens for specific sounds. Training these in Python is comfortable. Shipping them is
AI
Every Everbowl device sits in someone's home. It watches a dog eat, drink, move, and breathe — tracking feeding patterns, drinking patterns, eye temperature, and ambient sound to keep a quiet, continuous check on the pet's health. It is expected to run reliably for years, update silently
Firmware
In the high-stakes world of embedded firmware development, "optimization" is usually the golden word. We optimize for speed, for power consumption, and perhaps most frantically, for memory. We count bytes like misers counting pennies, shaving off struct padding and squashing enums into uint8_t wherever possible. We analyze
Hardware
A sensor board that is accurate at 25°C on a clean bench is not a finished product. It is a starting point. The moment that board ships inside a real device, it stops living at 25°C. It sits next to a regulator that warms under load. It is
Firmware
The build failed at 11 PM on a Thursday. Not from our code — from a missing pkg-config path. The CMake configure step for Mosquitto was resolving openssl.pc from /usr/lib/x86_64-linux-gnu instead of from the target sysroot. We'd seen this class of error before. Fix it,
Firmware
A customer's home hub stops sending data to the cloud. Logs go quiet. The Linux side looks fine — the bridge service is alive, the CAN driver is alive, but the wireless SoC it talks to over USB-CDC is silent. The chip enumerates as a serial device, so the
AI
When teams build their first Retrieval-Augmented Generation (RAG) chatbot, most of the engineering effort goes into chunking, embeddings, and vector search. That is exactly where we started at Hoomanely. But after months of iterating on a pet-health assistant grounded in veterinary books, nutrition manuals, and clinical PDFs, we hit a
Hardware
Designing hardware for a single feature turning on is relatively easy. Designing hardware for multiple subsystems waking up together without destabilising the system is where real embedded power architecture begins. Most embedded products today are no longer simple MCU boards with a few peripherals. A modern edge device may contain