The mental models a data professional needs to use AI well, from how language models read a schema to where embeddings beat classic feature engineering.
Paste any text to estimate how many tokens it uses, and see what that text would cost to send to each major model.
A model does not read your database the way you do. Understanding what it actually sees explains most of its confident, wrong joins.
Vectors are not a replacement for feature engineering. Knowing which problems they fit saves you from an expensive detour.
Three concepts explain most of what surprises analysts about LLM behavior, cost, and reliability. Here is what each one actually controls.