Using LLMs well

Go from typing into a chat box to calling a model from code.

1. What actually makes a prompt work Write prompts with context, task and format instead of hoping.
2. System prompts, user prompts and roles Put persistent instructions where they belong. coming soon
3. Getting structured output you can parse Make a model return JSON your code can rely on.
4. Call an LLM API from Python Make your first API call and handle the response in code.
5. Context windows, tokens and what things cost Estimate the cost and the context limit of a call before you make it.
6. Write your first eval Measure whether a prompt change actually helped.

Ends with a graded checkpoint: 10 questions, pass mark 70%.