What runs where, and who may start it
The question is no longer “ChatGPT, yes or no”. The question is what runs where and who may start it. Local and in-house AI is growing alongside the cloud: a Mac mini handles inference, open weights keep closing the gap, and agents are the product of the year and the risk of the year. This series takes you from your first local model to a control room you run the whole thing from — and to the rules without which it all falls apart.
45 parts · six tracks · more coming
Read it front to back like a course, or jump around by tag. If in doubt, start with the first part of each track — they assume you have installed nothing yet.
Prefer a fixed order to a signpost? Follow the path An agent on your NAS from scratch (13 steps).
01 · 5×
Model, harness, agent — and why the question moved from “AI yes or no” to “what runs where”.
02 · 5×
Two complete setups from hardware to invoice: what runs where, what it costs and why it is put together this way.
03 · 5×
Your first model on your own machine: Mac mini, Windows with an Nvidia card, memory, and when local is enough.
04 · 6×
One gateway in front of every model, API keys in one place, and routing each job to what handles it best.
05 · 8×
A control room in your pocket: Telegram as the panel, a safe route home, and a queue you approve yourself.
06 · 8×
Files from your disk into the chat: how it really works, what RAG is, what MCP does, what stays off the cloud.
07 · 8×
Agents are the product of the year and the risk of the year. One page of rules and the case studies behind them.
Tags
15 parts tagged “Orchestration” · Clear filter
Five accounts, three subscriptions, every model in a different tab and the files still sitting on disk. This part is the map of the whole series: what a control room is, which four layers it consists of and in what order to build it.
The model is the engine, the harness is the car, the agent is a driver with a job to do. If you don't tell these three layers apart, you can't make sense of a single news story about AI — or decide what to run at home and what to leave in the cloud.
“Do we use AI?” is a question from 2023. Today everyone gives the same answer and it tells you nothing. The useful question has two halves — where that particular task runs and who is allowed to start it — and the answer fits on one page.
A specific person, specific hardware, specific accounts. What runs where, what can be cancelled, when it pays to move from a subscription to the API — and in what order to build it so that each step makes sense on its own.
An account, a connected GitHub, a first brief — and within a few weeks a website that finds its own topic every morning, writes an article and waits for you to approve it. That's exactly how the site you're reading came about.
Five models, five apps, five keys, and nobody knows what it costs. A gateway is a single endpoint with everything hidden behind it — the local model at home and the most expensive one in the cloud. And swapping one out takes a single line.
A key is a password nobody changes, because nobody remembers it exists. Where to store it on a Mac, on Windows and on a server, why it does not belong in a chat or in a file in the project, and how to tell that it has got away from you.
Sending everything to the smartest model is like driving a lorry to the corner shop. How to split work into three tiers, set up a fallback route and stop paying for work the box in the living room can handle.
A local model isn't free and the cloud isn't expensive — until you start counting volume. How to work out your own break-even point, where the costs nobody tells you about are hiding, and why money isn't the main reason for going local anyway.
One account, one key, one invoice — and access to models from dozens of providers. What it really costs, how to set a spending cap, when it suits as your main route and when only as a safety net for an agent.
An agent doesn't have one price. It has four components, three of which are predictable while the fourth can spring a surprise. How to measure them, a table to fill in, where the money most often goes missing, and five levers for cutting the bill without losing the benefit.
Three devices, three different roles and one shared memory. How to divide up what gets done where, so that work in progress does not get left on the machine that happens to be shut in your backpack.
Uploading a thousand documents to a model and expecting it to know them doesn't work. How search over your own material really operates, why it most often fails on bad data, and what to do to make it answer correctly.
In March 2026 a modified version with a credential harvester made its way into the package of a popular AI gateway for forty minutes. Forty minutes was enough. What happened, why it's a warning for anyone building their own control room, and what to do about it.
An agent you have to explain everything to again is just a more expensive chat. A skill is a written-down procedure that it loads by itself next time. How one comes about, what it looks like inside, how to fix it — and why an agent's learning should pass your review just like everything else.
Get the next part
New parts and what matters in the world of agents go out in the weekly newsletter.
The Top 30 tips e-book, free — it lands in your inbox right away.
Then 1 tip a week · no spam · unsubscribe in one click