A program is made of prompts; steps fetch things from outside it. Prompts change during a run. Steps do not.
From an empty canvas (or a library template) to a finished run, in the order you will actually do it.
The words this product uses, and the words it deliberately does not. Worth five minutes: two of them used to mean four things each.
Prompts, placeholders, output fields, edges and what they carry, routers, the entry and terminal prompts, and the limit on loops.
What a row looks like, choosing the label column, the hold-out, and the pilot that prices a run before you start it.
Scorers, the metric vector, and how the objective weighs accuracy against prompt length.
The search loop, the minibatch gate, rounds and budget, Explore versus Guided, and how to read a run without fooling yourself.
Calling a service the optimizer never rewrites: manifests, signing in, freezing for training, and the eight validation checks.
Publishing an immutable version, its endpoint and API key, traces, outcomes, and promoting corrections into a dataset.
Five different secrets with five different jobs, where each one lives, and the rule that decides.