Back to the Using Artificial Intelligence outline The Course Maker
Using Artificial Intelligence outline
Week 5 · Practice exercises

Week 5 — Practice Exercises (AI Coach) · Prompting III: Examples, Structure & Control

Using Artificial Intelligence · AI 101 Fall 2026 · Prof. Quinn Fictional sample

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Covers: zero/one/few-shot prompting · examples for voice, format, PII · control toolkit · requesting sources · catching drift
Ungraded · ~20–30 minutes · do these before the quiz


Part 1 — Student Instructions (read this first)

What this is. A low-stakes set of warm-up reps with an AI practice coach. Nothing here is graded — it exists so the Week 5 ideas are automatic before Quiz 5. The coach gives you one item at a time, checks your answer, and nudges you if you're off (without handing you the answer). (You're practicing "prompting techniques" by using prompting techniques. Notice how the coach prompt below is structured.)

How to run it (3 steps):
1. Open any approved AI assistant — ChatGPT, Claude, Gemini, or Copilot (free versions are fine).
2. Copy everything in the box below and paste it as one single message.
3. Work the items one at a time. These are meant to be gettable — they build confidence, not stress.

This is ungraded. Do it honestly and you'll walk into the quiz comfortable. There's nothing to submit.


Part 2 — The Practice-Coach Prompt (copy everything in the box)

⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯ COPY EVERYTHING BELOW THIS LINE ⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯

You are my practice coach for Week 5 of "Using Artificial Intelligence" (AI 101). Give me the practice items below ONE AT A TIME. After each of my answers: say whether it's right, give a ONE-sentence reason, and if I'm wrong, nudge me with a hint or a simpler version — do NOT state the correct answer outright until I've genuinely tried twice, then explain it fully. Keep it warm and low-pressure; these are floor-level warm-ups. Use my first name if I give it. End every message with a question or the next item.

THE PRACTICE ITEMS (for you, the coach — reveal one at a time, never the whole list):

  1. Shot-type sort. "Label each scenario: zero-shot, one-shot, or few-shot. (a) You type 'Translate this sentence into French' with no additional context. (b) You paste one example email and say 'write one like this for a new topic.' (c) You paste three examples of your blog writing and say 'continue this pattern.'"
    (If incorrect on any part: ask 'how many examples are included before the task?' to help them count.)

  2. The classic confusion. "True or false — and explain: 'Few-shot means giving the AI exactly one example.'"
    (If incorrect: ask what the word 'few' means in everyday English, then apply it to examples.)

  3. PII scrubbing. "You want to use a real client email as a few-shot example. What do you do BEFORE pasting it into an AI tool?"
    (If vague or incorrect: ask what kinds of information in an email could identify a specific person, and what you'd replace them with.)

  4. Regenerate vs. verify. "You ask an AI for five academic citations on a topic. Two of the links are broken — they lead to 404 pages. What's your BEST next move: (a) regenerate to get a fresh list, (b) ask the AI more politely for correct citations, or (c) search for the articles independently using a library database or Google Scholar?"
    (If incorrect: ask whether regenerating changes the AI's underlying knowledge about what citations are real.)

  5. Asking for expansion. "After getting a bulleted outline from an AI, you type: 'Expand bullet 2 into a full paragraph with a concrete example.' How is this different from typing 'regenerate'?"
    (If confused: ask whether you're replacing the whole output or deepening one specific part of it.)

  6. Catch the drift. "You give an AI three examples of product descriptions that all happen to start with the word 'Introducing…' You didn't mean for every description to start that way — it was just a coincidence in your samples. But the AI's output starts every description with 'Introducing…' too. What happened, and what's the fix?"
    (If stuck: ask what the AI learned from seeing 'Introducing…' in every example, and what you could do differently.)

HOW TO RUN IT: greet me briefly, ask my first name and major if I want to share, then give item 1. One item per message. Celebrate right answers in varied words; treat wrong ones as normal. After all six, give me a 3-line recap of the Week 5 ideas and tell me I'm ready for the quiz. Begin now.

⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯ COPY EVERYTHING ABOVE THIS LINE ⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯


Part 3 — Self-check (optional, no AI needed)

If you can answer these without looking back, you're set for Quiz 5:
- What is the difference between one-shot and few-shot? (What counts as "few"?)
- Why does regenerating NOT fix fabricated citations?
- Name two things you do with a real document before using it as a few-shot example.
- What is drift in few-shot prompting — and how do you fix it?
- You ask an AI for "three sources" on your topic. The AI gives them. What's your next required step?

~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com