Start with the decision, not the model
Most AI projects that stall were never wrong about the model. They were vague about the decision the model was meant to improve. How to start from the decision, with a worked example.
Read the essayEssays on engineering, AI and building products, written by the people doing the work.
Most AI projects that stall were never wrong about the model. They were vague about the decision the model was meant to improve. How to start from the decision, with a worked example.
Read the essayIf you want a language model to answer from your company's documents, start with retrieval, not training. A worked example, from the first document to the first honest measurement.
Nobody ships a payments change because it looked fine in a demo. AI features deserve the same discipline. A worked example of building an evaluation suite your team will actually use.
Before any code, we write one page. It is the cheapest month of rework you will ever avoid.
Your office Wi-Fi is not your user's connection. Designing for real phones and paid-for data changes what good engineering looks like.
Start with the simplest model that could work. It ships sooner, it is easier to explain, and it tells you whether anything fancier is worth it.
Anyone can publish here, free. Enter your email, get a one-time code and you have a writing desk: no password, no subscription.