operations

How Much of Your Platform Are You Actually Using?

Fifteen questions, about four minutes. Scores your estate across five areas and tells you what I'd do next in each one. Nothing is sent anywhere.

Fifteen questions, about four minutes. It scores your estate across five areas and tells you what I would do next in each one.

Answer honestly rather than aspirationally. Nothing is sent anywhere, nothing is stored, and the result is only as useful as the inputs. If you are unsure about a question, pick the lower option, because the gap between what a team believes is configured and what actually is tends to run in one direction.

What You Already Paid For and Haven't Switched On

A customer asked what database monitoring would cost. Ten minutes in it was clear they already had it. Entitled, not deployed, nobody had looked.

RAG Is a Distributed Systems Problem

Five stages in the path, and only the last two involve the model. Retrieval is memory bound, generation is GPU bound, and they do not belong on the same hosts.

Which Inference Engine, and Does It Matter?

They implement the same ideas. The difference is what each optimises for and what it costs you to run, which is a less exciting answer than people want.

What Does a Token Actually Cost You?

The arithmetic is easy. The denominator is where models fall apart, and the biggest lever has nothing to do with hardware.

Read more

What You Already Paid For and Haven't Switched On

RAG Is a Distributed Systems Problem

Which Inference Engine, and Does It Matter?

What Does a Token Actually Cost You?