BLOG

notes from the running system – pinned as they ship

While I sleep: the system catches every incoming

An email at 3am, a document dropped into a chat on Sunday, a new court filing on a holiday – a person misses these, the system doesn't. It's always online, catches every incoming signal, and decides whether to wake me or let it wait until morning.

read →

Reconciled to the cent: what real reconciliation means

Reconciling statements to the cent means understanding what each line actually does, not just adding up totals. How the system does it and what hides behind the word 'deposit'.

read →

Autonomy hours: the metric I build the system around

Not how many tasks the AI closed, but how many hours a day the business runs without me at the screen. How I measure it, what runs while I'm away, and why the target is four hours by December.

read →

Memory matters more than the model

A chatbot answers and forgets the conversation. The system remembers your business: counterparties, contracts, the history of decisions. The model swaps out in a day, the accumulated memory doesn't. That's where the moat runs.

read →

Decisions from your phone: running the system with one tap

My system's interface is a Telegram chat, not a dashboard. Each morning a short list of what's stuck on my decision shows up, and I clear every item with one tap, without opening the laptop.

read →

A system live in one day

AI rollout usually means a project that runs for months. For the first client the whole system landed on the manager's laptop in a day, with a Telegram bot as the way in. Why it's that fast, and where the real work is.

read →

What local models can actually handle

Can a business run its operations – mail, bank, contracts – on a model sitting on your own hardware? Numbers from a live system: a local model covers 81% of the work, only a trimmed slice goes out with a log, and the line keeps moving toward local.

read →

Token economy: an LLM infrastructure for half a dollar a week

855 calls in a week, a $0.50 bill. How an infrastructure works where a local model takes 81% of the load and the cloud joins only after measurements say so.

read →

What an AIOS is and why a business needs one

An AI operating system sorts your inbox at six in the morning while you sleep. How it differs from a chatbot, the five layers it's built from, and why you start with context, not the model.

read →