Foundations
The ideas the rest of the docs assume you already have.
The rest of the documentation shows you how to do things. This section explains what those things are.
If you've shipped an LLM feature before, skim it. You know most of this already. If you haven't, these five pages are the fastest way to stop guessing at why a call behaved the way it did.
The loop
Call, tool calls, execute, feed back, repeat. Everything else is a variation on this.
Models and tokens
Context windows, why the same prompt gives different answers, and what temperature actually does.
Prompts and messages
Why history is a list, what a role is for, and why the model has no memory.
Tool calling
The model never runs your code. What it actually emits, and who executes it.
Streaming
What a stream carries besides text, and why it changes how you write the call.