Week 9 Quiz — The AI Tool Landscape: Choosing the Right Tool

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Covers: AI tool categories (chatbots, image, audio/music, video, research, coding) · tool→best-use matching · mis-matched tool recognition · when not to use AI
Format: 10 auto-graded items (multiple-choice, multiple-answer, matching, true/false) · 10 points (1 each) · allowed attempts: 1 · No AI on this quiz.

This is the human-readable quiz with its vetted answer key and one-line feedback. The import-ready Classic QTI 1.2 is in F-quiz-week-09-qti.xml (generated by a validated Python script — parses with 10 items, every single-answer item exactly one correct). Reminder: AI is not permitted on quizzes — this checks that you understand the Week 9 ideas.

Questions, key, and feedback

Q1 (MC). A student wants to generate an original 60-second audio jingle for a class project. She types her prompt into ChatGPT. What is the most likely problem?
- A. ChatGPT will refuse to help with creative projects
- B. ChatGPT is a text tool and cannot produce audio output — she needs a music generation tool such as Suno or Udio ✅
- C. ChatGPT can generate audio files but only on paid plans
- D. ChatGPT will produce audio but it will be lower quality than a specialized tool
Feedback: ChatGPT (and chatbots generally) generate text. They cannot produce an audio file. For original music audio output, use a music generation tool in that category — Suno (https://suno.com) or Udio (https://udio.com).

Q2 (Matching). Match each AI tool or tool category to its best-fit use case.
| Tool | Best-fit use case |
|---|---|
| NotebookLM (Google) | Analyze and surface themes from documents you upload |
| ElevenLabs | Convert a script into a realistic human-sounding voiceover |
| Midjourney | Generate a visual concept image from a text description |
| GitHub Copilot | Get context-aware code suggestions integrated into your editor |
Feedback: Each tool belongs to a distinct category: NotebookLM = research assistant (your documents); ElevenLabs = voice synthesis; Midjourney = image generation; GitHub Copilot = coding assistant embedded in your workflow. The key skill: matching the tool to the type of output the job needs.

Q3 (MC). What is the key difference between NotebookLM and a general-purpose chatbot like Claude or ChatGPT?
- A. NotebookLM can only handle documents shorter than 10 pages
- B. NotebookLM generates answers from general training data, while chatbots only use your uploaded files
- C. NotebookLM is grounded in the specific documents you upload and cites from them, rather than drawing on general training data ✅
- D. NotebookLM is a coding assistant, not a research tool
Feedback: NotebookLM's defining feature is that it answers from your uploaded documents and cites them — not from general training. A chatbot draws on general training; it doesn't "know" your 40-page research file unless you paste it in. Different tool, different job.

Q4 (MC). A student wants detailed, current pricing information for three AI image generation tools. She asks a chatbot, which gives her a confident list of prices. What is the most important fix to her workflow?
- A. She should ask the chatbot to search the internet for current prices
- B. She should verify every price directly on each tool's official homepage, since chatbots can give outdated or fabricated pricing information ✅
- C. She should use a different chatbot, since some are more accurate about pricing
- D. She should accept the chatbot's list, since AI tools are required to be transparent about pricing
Feedback: Specific pricing details are exactly the kind of fact chatbots get wrong or out-of-date. The only reliable source for current pricing is the tool's official homepage. This is the verification habit applied to a tool-landscape question — the same rule as always: verify specific claims at the authoritative source.

Q5 (True / False). The newest AI tool released is always the best choice for any given job.
- True
- False ✅
Feedback: False. Recency ≠ fit. A specialized tool built specifically for your job — even an older one — will usually outperform a brand-new general-purpose tool that handles your job as a secondary feature. Always evaluate for the specific task, not the launch date.

Q6 (Multiple answer — select all that apply). Which of the following are music generation tools — meaning they can produce actual audio music output from a prompt? Select all that apply.
- A. Suno ✅
- B. ElevenLabs
- C. Udio ✅
- D. NotebookLM
- E. Midjourney
Feedback: Suno (https://suno.com) and Udio (https://udio.com) are music generation tools that produce audio output. ElevenLabs makes voices (voice synthesis/text-to-speech), not music. NotebookLM is a research assistant. Midjourney is an image generator. The Suno/Udio vs. ElevenLabs distinction is this week's most commonly tested confusion.

Q7 (MC). Which of the following is OpenAI's video generation tool — designed to generate video clips from text prompts?
- A. DALL·E
- B. Suno
- C. Sora ✅
- D. Copilot
Feedback: Sora (https://sora.com) is OpenAI's video generation model. DALL·E is OpenAI's image generation model. Suno is a music generation tool (not made by OpenAI). Copilot is Microsoft's general-purpose AI assistant.

Q8 (MC). A graduate student has 30 pages of interview transcripts and wants to identify the most common themes across all of them. Which tool category is the BEST fit?
- A. Image generation — to visualize the data patterns
- B. Music generation — to set the mood for analysis
- C. Research assistant / notebook tool — grounded in the specific documents she uploads ✅
- D. Coding assistant — to write a script that parses the transcripts
Feedback: When the job is analyzing your specific documents (not generating content from scratch), a research assistant / notebook tool like NotebookLM is purpose-built for this. It works from her transcripts and cites them. A general chatbot could help if she pasted the transcripts, but NotebookLM is designed exactly for this workflow.

Q9 (MC). Which of the following is the BEST example of a task that should NOT be delegated to AI, even with a capable tool?
- A. Brainstorming five possible titles for a personal essay
- B. Summarizing a long article you already read and understood
- C. Making the final decision about a major career change, based only on AI's recommendation without applying your own judgment ✅
- D. Generating a first draft of an email to a professor
Feedback: Deeply personal major decisions require your judgment. AI can help research options, model scenarios, or surface considerations you hadn't thought of — but accepting an AI recommendation as the final answer on a major life decision bypasses the judgment that only you can apply. Options A, B, and D are reasonable AI-assist tasks where the human stays in the loop.

Q10 (Matching). Match each AI assistant/chatbot to the company that makes it.
| AI assistant | Company |
|---|---|
| Grok | xAI |
| Claude | Anthropic |
| Gemini | Google |
| Copilot | Microsoft |
Feedback: Tool→maker matching is practical knowledge for the landscape: Grok is from xAI (Elon Musk's AI company); Claude is from Anthropic; Gemini is from Google; Copilot is from Microsoft (powered by OpenAI models but a Microsoft product). ChatGPT and DALL·E are both from OpenAI.

Answer key (quick reference)

Blueprint & item-bank note

All 10 items tagged course=AI101 · week=9 · objective=3 and deposited into the item bank. Matching items include ≥1 tool→best-use matching (items 2 and 8). Item 4 is the required "what's the fix?" scenario item. Distractors target classic confusions: chatbots doing everything; image generators = chatbots; newest tool = best; ElevenLabs = music (it's voice); NotebookLM = chatbot.

Quality gate (self-checked)

• Structure: 10 items, 1 point each; types = 6 multiple-choice + 2 matching + 1 multiple-answer + 1 true/false.
• Single-answer integrity: every MC and the true/false item has exactly one correct option; the matching items pair one-to-one; the multiple-answer item keys A, C only.
• Tool claims verified: every tool named (ChatGPT, Claude, Gemini, Copilot, Grok, DALL·E, Midjourney, Adobe Firefly, Suno, Udio, ElevenLabs, Sora, NotebookLM, GitHub Copilot, Cursor, Claude Code) is a real, current product. No version numbers, pricing, or feature specifics asserted — only category-level capabilities, which are publicly documented. Official links provided in B-, H-, and C- files.
• Product-accuracy gate: PASS. No fabricated features; all tools named factually; Q4 specifically models the correct behavior of verifying tool-specific claims at the official homepage.

Canvas placement block

canvas_object    = Quizzes::Quiz
title            = "Week 9 Quiz — The AI Tool Landscape: Choosing the Right Tool"
assignment_group = "Quizzes"
points_possible  = 10
grading_type     = points
available_from_offset_days = 0
due_offset_days  = 6
published        = true
allowed_attempts = 1
shuffle_answers  = true
ai_permitted     = false
provenance       = "~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com"