Knowledge base
Short pieces on implementing AI in a small company so that it works and can be explained to the board. No jargon where it can be avoided, setting names where they are needed.
Anatomy of the Monday report
The Monday report is the most common first AI project in a small company, because it is measurable: you know how long it took, and you can see when it arrived. Here is what it is made of, step by step.
What not to paste into AI
The biggest AI risk in a small company is not in the model. It is in the employee who, at ten to five, pastes a client contract into a personal chat account to “summarise it quickly”. Here are rules you can introduce in a week.
MCP on a read-only account
Connecting an assistant to company data takes fifteen minutes these days. Doing it so that nobody regrets it six months later takes an hour longer. That hour is a separate account, read-only access and a log.
Human in the loop
“AI does not send, delete or pay without a person confirming” sounds good, but in practice you have to decide exactly what gets confirmed, by whom, and for how long. Here is the table I use.
What you will not find here
No model rankings and no predictions of what AI will do in five years. Just the things I check and set up on every implementation. If a topic that stopped you is missing, write to me: I will answer and, if the question keeps coming up, add an article.
Would you rather your team learnt this themselves than outsource it?
AI training for teams: on your own tasks, with clear rules on what not to paste into AI.