Week 7 — Practice Exercises (AI Coach) · Multimodal AI: Voice, Audio, Images & Documents

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Covers: voice prompting · the record → transcribe → analyze workflow · the multimodal task map · tool → modality matching · catching transcription errors and summary fabrications
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 7 ideas are automatic before Quiz 7. 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).

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 7 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. Voice prompting check. "True or false: when you speak a prompt to an AI assistant using voice mode, the AI processes your audio directly without any intermediate steps." (If incorrect: ask what happens between the moment you speak and the moment the AI processes your words — is there a conversion step?)

2. Three-step workflow sequence. "Put these three steps in the correct order for the record → transcribe → analyze workflow: Paste the text into an AI assistant and ask for a summary. / Open a transcription app and convert your recording to text. / Record your voice memo or meeting with a recording app." (If incorrect: ask which step has to come first — can you convert audio before you've recorded it?)

3. Error-entry points. "Name the TWO main places where errors can enter the record → transcribe → analyze workflow." (If incorrect: ask 'where does the text come from?' and 'once the AI has the text, what could it add or miss?')

4. Tool → modality matching. "Match each task to the right tool type — transcription tool, multimodal chatbot with image upload, or text-to-image generation tool: (a) convert a voice recording to text; (b) ask an AI to extract text from a photo of a receipt; (c) generate a new image from a written description." (If incorrect: ask 'is the task producing text from audio, text from an image, or an image from text?' — the direction of the conversion helps.)

5. Confusing image creation vs. image analysis. "A student says: 'I used DALL·E to analyze what's in this photo.' What's wrong with that statement?" (If incorrect: ask 'what does a text-to-image tool take as INPUT and what does it produce as OUTPUT?' — is analyzing a photo the same direction?)

6. Catching a summary fabrication. "You transcribed a 10-minute meeting and asked an AI for a summary. The summary mentions 'a decision to move the deadline to November 15' — but you don't remember that being decided. What's your next move?" (If incorrect: ask 'should you trust the summary or the transcript — which one came directly from the audio?')

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 7 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 7:
- What are the three steps of the record → transcribe → analyze workflow, in order?
- Name two places errors can enter that workflow.
- For each task, what type of tool would you use: (a) generating an image from text; (b) extracting text from a photo; (c) converting a meeting recording to text?
- What is the difference between image analysis (image → text) and image creation (text → image)?
- True or false: chatbots are text-only and cannot process images or audio.