My automations are good at thresholds and bad at context. Jev answers typed questions with a calibrated probability, for about two thousandths of a cent each. Here is how I wired it into Home Assistant with the old rules kept as a safety net, and what it really costs.
My first model router let an LLM read a prompt file and pick an agent. This one asks a “System One” decision model four typed questions, scores the models with plain arithmetic, and publishes a benchmark to prove it works (and to show where it doesn’t).
E2E encryption means Proton can never index your photos. So I built a two-container search engine that does it locally, on my own hardware, without ever writing back to Proton.
A Zigbee smart plug, nine automations, and one invisible pump that saves the house from flooding - the “invisible device” pattern, monitored with Home Assistant.
