Skip to main content

Level 4 of 9

Intermediate 1: LLM builder

At the end you can: Call an LLM API; manage prompts, tokens and context; get structured JSON output; handle errors and cost.

About 20 hours in all; the steps written so far take about 15.

Steps

  1. Call an LLM API from codeSend a prompt to a language model from a Python script and use the reply in your program.Not started · about 3 hours
  2. System prompts and prompt designWrite system prompts and instructions that give clear, repeatable results, and improve them by testing.Not started · about 4 hours
  3. Tokens and the context windowExplain what tokens are, estimate the cost of a request, and keep inputs inside the context window.Not started · about 2 hours

Sign in or sign up to see the full roadmap

All 6 topics in order, with your progress saved on every device. It takes a few seconds, no card needed.

Accounts are for learners aged 18 and over. Under 18? Every lesson is still open: browse lessons by topic.

Level project

A small web or command-line app that uses an LLM API.

Today's AI turns are used

Lessons, roadmaps, videos, practice cards and the code playground stay free with your account, with no limit.