skill~120 mindifficulty

Calling LLM APIs

Every GenAI app is built on top of a handful of API calls, so this is the foundational skill.

1

Learn it

Follow the official OpenAI quickstart to create a key, install the SDK, and run your first text-generation call from Python. Then read the text-generation guide to learn how system/user messages and generation parameters shape the output. Store your key in an environment variable, never in code.

By the end you’ll be able to

  • Make an authenticated API call from Python and parse the response
  • Control output with temperature, max tokens, and system messages

Free resources

2

Practice

Write a Python script that takes a topic from the command line and returns a 3-bullet summary, exposing temperature as a tunable argument.

3

Build it — your output

A reusable Python function that wraps an LLM call with configurable system prompt and parameters.

4

Prove it — check yourself

You’re ready to move on when you can honestly say yes to each:

  • Can you make an API call and read the model's text from the response?
  • Can you explain what temperature and max tokens do?
  • Are your API keys kept out of source control?

Do it with AI

Use a free AI tool as your tutor and pair-programmer. Copy a prompt below into Claude, ChatGPT, or Gemini (for building, try Cursor or Copilot).

The habit: Try it yourself first — a little struggle is where the learning actually happens. Then ask for a hint before the answer — never copy blindly.

  • Understand itClaude / ChatGPT / Gemini

    I'm a beginner learning "Calling LLM APIs". Explain it in simple terms with a real-world analogy, then ask me ONE question to check my understanding — don't reveal the answer.

  • PracticeClaude / ChatGPT / Gemini

    Give me 3 short practice problems on "Calling LLM APIs" (my goal: make an authenticated api call from python and parse the response), from easy to hard. Don't include the solutions yet — I'll try them first, then ask you to check.

  • Get unstuckClaude / ChatGPT / Gemini

    I'm stuck on this exercise about "Calling LLM APIs": [paste your attempt here]. Give me ONE small hint to move forward — do NOT give me the full solution.

  • Build & reviewCursor / Copilot

    Here is my work for a "Calling LLM APIs" task: [paste your code or answer]. Review it: point out what's wrong and WHY, and suggest improvements — but let me make the fixes myself.

  • Prove itClaude / ChatGPT / Gemini

    Quiz me on "Calling LLM APIs". Ask me 5 questions one at a time, wait for my answer each time, then tell me if I'm right and briefly why.

My notes