Why should a developer never access the Anthropic API directly from a web or mobile app?	Because the request requires a secret API key, which must never be included in client-side code.
What are the four essential pieces of data required when a server makes a request to the Anthropic API?	An API key, the name of the model, a list of messages, and a max tokens value.
In the text generation process, what is a token?	A smaller string unit of text, which can be a whole word, part of a word, a space, or a number.
What is an embedding?	A long list of numbers that serves as a number-based definition of a given word.
What is the purpose of contextualization in the text generation process?	To adjust each embedding based on surrounding embeddings, refining its meaning based on its neighbors.
How does the language model select the next word during the generation stage?	It uses a mix of probability and randomness, rather than automatically picking the highest probability.
What are the two primary conditions that cause the model to stop generating text?	Reaching the max tokens parameter or generating a special end of sequence token.
What three pieces of information are included in the API response after text generation?	The generated message, usage count (input and output tokens), and the stop reason.