Blog
Deep dives, notes and lessons from our directions: RAG and agents, speech, vision, automation, robots.
An assistant that books: how we added clients, schedules and Telegram, Max and website channels to GraphRAG
An assistant that only answers leaves people the hardest part: booking, reminding, inviting clients back. We added a Clients module to GraphRAG with services, schedules and message scenarios, connected Telegram, Max and a website widget, and wrote a separate gateway for regular company accounts. Here are the decisions we made, what we threw away and where the limits are.
Read →An agent instead of a script: we moved an AI assistant's logic into data and tested it on 300 questions
Knowledge-base assistants are usually built as a pipeline (router → retrieval → answer), and every new kind of question adds a branch. In GraphRAG we replaced the pipeline with an agent that has eight tools, and moved everything that must always happen into a versioned, tested JSON harness. How it works, what a blind comparison on 300 questions showed, and where the agent still loses.
Read →A local AI video editor: how a laptop reads a media library and cuts a clip to music from a text prompt
A trip left me with a hundred phone videos and a dozen tracks, and the editing kept slipping for weeks. So I built an app that analyzes the library with a local vision-language model, marks up the music by beats and bars, and turns one sentence into a rough cut on the timeline. What it does, which rakes I stepped on, and what it will not do.
Read →Powering your home PC from vacation: a $2 ESP32, Wake-on-LAN and MQTT
I left on a long vacation while my RTX 5090 machine sat at home, occasionally needed for AI. Keeping it running around the clock felt wrong — so I built a $2 alarm clock on an ESP32: one button on my phone, the board wakes the computer over Wake-on-LAN, and once Windows is up I can do anything with it — down to exposing the local Ollama through a reverse SSH tunnel.
Read →