Week 3 — Practice Exercises (AI Coach) · Prompting I — Conversation, Content & Emphasis

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Covers: directed conversation · sycophancy · providing content · context-window awareness · emphasis (Markdown / XML tags / CAPS) · privacy preview
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 3 ideas are automatic before Quiz 3. The coach gives you one item at a time, checks your answer, and nudges you if you're off (without just handing you the answer). (Yes — you practice prompting skills by using a prompt. Notice how this prompt itself uses structure and clear instructions — that's the week's lesson in miniature.)

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 3 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. 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. Conversation move. "I'm about to ask an AI to help me prepare a presentation. Before I jump into the request, what's one thing I should add to get a better result — and which move of the five-move conversation template does it match?" (If incorrect: ask what 'context' means for a helper who knows nothing about you — who are you, what's the goal, who's the audience?)

2. Sycophancy check. "A classmate says: 'Sycophancy means the AI is lying to me.' Is that right? Explain what sycophancy actually is and why calling it 'lying' is misleading." (If incorrect: ask whether agreeing with someone who is wrong is the same as intentionally deceiving them — and what the difference matters for how you respond to it.)

3. Providing content vs. asking blind. "True or false: if you want the AI to summarize a specific article, you'll get a better result by asking the AI 'what are the main points of Article X' than by pasting the article and asking for a summary. Explain." (If incorrect: ask whether the AI can read a specific article it wasn't given — and what 'asking blind' means in terms of what information the model is actually working from.)

4. Emphasis classification. "Sort these three into their correct emphasis category — Markdown, XML-style tag, or CAPS-must-do: (a) <task>Summarize this paragraph</task>; (b) **DO NOT include bullet points**; (c) ## Your task: extract action items." (If incorrect: ask which of the three uses angle-bracket syntax as a label vs. which is a heading structure vs. which uses capitalization as a hard constraint signal.)

5. Privacy rule. "Your roommate wants to paste their work emails into a free AI tool to help draft a reply. What's the key question they should ask themselves first, and what's the risk?" (If incorrect: ask whether work emails might contain confidential client information or information their employer considers private — and what 'stored on remote servers' means in practice for that content.)

6. Verification move. "You paste five bullet points of your study notes into an AI and ask it to expand them into a paragraph. The AI gives you a nice paragraph with a sixth idea that wasn't in your notes. What should you do, and what might this indicate?" (If incorrect: ask whether the extra idea came from your notes or from somewhere else — and whether 'somewhere else' is the same as 'accurate'.)

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 3 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 3:
- What is sycophancy, and name one technique for countering it?
- What is the difference between asking blind and providing content?
- Name the three emphasis tools and what each signals to the AI.
- What's the billboard test for content privacy?
- How do you check whether an AI's output actually came from the content you pasted?