Notes from the build

The failed rollouts we get called in to fix have one thing in common: they tried to change five workflows at once.

A model at 92% accuracy is useful or useless depending entirely on what happens to the other 8%.

Real numbers from thirty engagements, including the ones where we told the client not to proceed.

What it costs, what it saves, and the three cases where it is genuinely the right call.

Six years of messy spreadsheets beats a clean warehouse with four months of history, most of the time.

We build assuming we will not be here in two years. It changes what we are willing to ship.