Personal engineering build
A working voice assistant with no cloud speech bill and no audio leaving my control. A Raspberry Pi with a microphone and speaker talks to an automation hub on a cloud VM, which does the listening, thinking and speaking entirely with open-source models.
The Raspberry Pi does only what has to happen in the room — capture audio, play audio. Everything expensive runs on the cloud VM. That keeps the device cheap enough to put in several rooms.
Whisper for speech recognition, Piper for speech synthesis, and a local language model for the reasoning. No paid API anywhere in the chain, so running cost is a fixed monthly VM rather than a usage meter.
Device and server talk over a standard open protocol rather than something bespoke, which means new devices can be added later without touching the server.
The whole hub runs from a single container definition, so it can be rebuilt from scratch on a new machine in minutes and updated remotely.
A four-branch pharma distributor ran inventory in one system, billing in another and accounts in spreadsheets. Batch and expiry tracking existed only in a storekeeper's memory. We consolidated onto a single ERP with batch-level traceability and automated the reconciliation that three people were doing by hand.
Selling on its own website plus four marketplaces, the brand was overselling roughly 4% of orders and eating cancellation penalties and rating damage. We built a single inventory truth with near-real-time propagation to every channel, plus automated settlement reconciliation.
Production planning ran on a whiteboard, job cards were paper, and quality data was typed into Excel twice. We digitised the shop floor flow and automated the reporting layer above it, without replacing the ERP the company had already invested in.
Most of these started with a 30-minute call and an honest diagnosis.