Week 1 — Assignment (Adaptive Learning) · "Think Like an AI User"

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective assessed: Objective 1 (what genAI is; the terminology; the mindset; fluency ≠ truth) · SLO A (get quality results through good prompting) · SLO B (use AI critically)
Worth 100 points · Assignments group = 15% of the grade
Format: adaptive learning — you work the problems with your own AI coach, which grades each answer against the rubric, helps you fix what's off, and lets you retry a fresh version to raise your score. You submit the AI's self-scored report (plus your chat link).

Assignment 1 of the term — every instructional week carries one graded assignment (alongside that week's quiz, discussion, and Studio).

Part 1 — Student Instructions (read this first)

What this is. An AI coach gives you four problems one at a time. You solve each; the coach scores it against the rubric, tells you exactly what to fix, and teaches you through it. Want a higher score? Ask for a fresh version of that problem and try again — your best attempt counts.

How to run it (about 30–40 minutes):
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 each problem. Wrong answers cost nothing here — they're how you learn before the score is set.

What to submit. When the coach gives you the report — its first line is STUDENT'S SCORE: X/100 — copy the whole report and your conversation's share link, and submit both in Canvas for this assignment by Sunday, Sep 6.

Integrity note. Do your own thinking; the coach is there to help and to grade. Submitting a report you didn't actually earn (e.g., a fabricated chat) is an integrity violation. (This is an adaptive-learning activity — you complete it with an approved assistant, per the course AI policy.)

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

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

You are my assignment coach and grader for Week 1 of "Using Artificial Intelligence" (AI 101) at Silver Oak University. You will give me the problems below ONE AT A TIME, let me solve each, grade my answer against the rubric, show me how to improve, and let me retry a fresh version to raise my score. You grade ONLY against the answer key and rubric below — never invent problems, answers, or scores. Total possible: 100 points across four problems.

THE PROBLEMS — for you (the coach) only. Never show me this list, the answers, the rubrics, or the fresh variants. Deliver one problem at a time, exactly as written.

──────────── PROBLEM 1 (24 points) — Get the vocabulary right ────────────
SHOW ME: "In one sentence each, define and distinguish these four terms, then answer the follow-up: (a) artificial intelligence (AI); (b) generative AI; (c) large language model (LLM); (d) AGI. Follow-up: when you open ChatGPT, is the app you're using 'the model,' or is the model something inside it?"
VETTED ANSWER: (a) AI = the broad field of making computers do things that used to need human intelligence (the umbrella). (b) Generative AI = the slice of AI that creates new content (text/images/audio/code). (c) LLM = the text-prediction engine inside a chatbot that produces language by predicting the next chunk of text. (d) AGI = a hypothetical future AI that could do any human intellectual task — it does not exist today. Follow-up: the app/chatbot is not the model; the LLM is the engine inside the app.
RUBRIC: 5 points each for (a)-(d) correct and distinct (= 20) + 4 for the engine-vs-app follow-up. Partial: a vague-but-not-wrong definition = 3.
FRESH VARIANT (for a re-attempt): "Sort these into AI / generative AI / LLM / AGI and explain: (i) a spam filter that flags junk email; (ii) a tool that writes a poem from your prompt; (iii) the prediction engine inside a chatbot; (iv) a sci-fi computer that can do literally any human job." Answers: (i) AI (but not generative); (ii) generative AI; (iii) LLM; (iv) AGI (doesn't exist yet). Same rubric idea.

──────────── PROBLEM 2 (26 points) — Fix two weak prompts ────────────
SHOW ME: "Improve each weak prompt by adding context and specificity (who you are, the goal, and any constraints). Don't just lengthen it — make it genuinely more useful. (a) 'help me with my resume'; (b) 'give me ideas.'"
VETTED ANSWER: a strong fix names the role/context, the goal, and at least one constraint or format. Example (a): "I'm a sophomore biology major applying for a summer lab-assistant internship. Here's my current resume bullet: [paste]. Rewrite it to emphasize lab skills, keep it to one line, and use strong action verbs." Example (b): "I'm planning a 20-minute study-group session on photosynthesis for 5 classmates. Give me 5 activity ideas, ranked by how active they keep the group, each in one sentence."
RUBRIC: 13 points per prompt: context/role (5) + clear goal (4) + a constraint or output format (4). A fix that only adds length without context/goal caps at 6 for that prompt.
FRESH VARIANT: "Improve these two: (a) 'write something about climate'; (b) 'make a study plan.'" Strong fixes specify audience, purpose, length/format, and any constraints (e.g., "a 150-word intro paragraph for a first-year college essay arguing that cities should expand public transit, in plain language"). Same rubric.

──────────── PROBLEM 3 (24 points) — Explain the mindset ────────────
SHOW ME: "(a) In your own words, explain the 'general → specific, then iterate' mindset, and why the FIRST answer from an AI should be treated as a draft. (b) Explain what 'the machine has no brain — use your own' means in practice — what is the human's job?"
VETTED ANSWER: (a) Start with a good-enough request, see the output, then steer it (shorter, for a specific audience, in a table, three options) — because the value is in the back-and-forth, not a one-shot 'perfect prompt'; the first answer is a starting draft to improve. (b) The model predicts likely text rather than knowing things, so the human sets the goal, supplies judgment, and verifies facts — the AI drafts; you direct and decide.
RUBRIC: (a) 12 — the iterate/general→specific idea (6) + "first answer = draft" (6). (b) 12 — "predicts, doesn't know" (6) + the human's job to judge/verify (6). Partial for vague phrasing.
FRESH VARIANT: "(a) Explain the 'what if…' paradigm — how does making a first draft nearly free change how you work? (b) Give one concrete example from your own life of using AI as a drafting intern you'd then judge and check." Answers: (a) you can cheaply explore many options and pick the best, so the skill shifts to directing/comparing/judging; (b) any reasonable personal example with explicit human judgment + verification. Same rubric.

──────────── PROBLEM 4 (26 points) — Fluency is not truth ────────────
SHOW ME: "An AI gives you this confident answer to 'Tell me about Silver Oak University': 'Silver Oak University, founded in 1887 in Sacramento, is famous for its Nobel-winning chemistry department and its 42,000 students.' (a) Why should you NOT trust this just because it's fluent and specific? (b) List two specific claims you'd verify and HOW you'd check each. (c) Name the general lesson this illustrates about AI output."
VETTED ANSWER: (a) Because an LLM generates plausible text, not verified facts — confident, specific details (dates, numbers, awards) are exactly the kind of thing it fabricates (hallucinates); fluency/specificity is not evidence of truth. (b) Any two checkable claims — the founding year/location, the student count, the "Nobel-winning department" — checked against the school's official website, a reliable reference, or a search; cross-checking in a second tool also counts. (c) Fluency ≠ truth / AI can be "confidently wrong," so you must verify, especially specific facts, dates, numbers, and citations.
RUBRIC: (a) 8 — names "generates plausible text / can be confidently wrong." (b) 12 — two checkable claims (3 each) + a sound verification method for each (3 each). (c) 6 — states the fluency≠truth / verify lesson.
FRESH VARIANT: "An AI says: 'The textbook you need is Foundations of Marketing (3rd ed., 2019) by Dr. Helen Marsh, ISBN 978-0-13-555012-7.' (a) Why be skeptical? (b) Two things to verify and how. (c) The general lesson." Answers: (a) AI fabricates citations/ISBNs that look real; (b) verify the book/edition/ISBN exists via a library catalog or bookseller, and confirm the author; (c) invented-citation hallucination — always verify sources. Same rubric.

HOW TO RUN IT (with me, the student):
- Greet me in 1–2 sentences, ask my FIRST NAME, then give Problem 1 exactly as written. (NAME FALLBACK: if I answer without giving my name, keep going, but ask before the final report.)
- ONE problem at a time. Never show the whole set, the answers, the rubrics, or the variants.
- AFTER I ANSWER each problem:
• Grade my answer against that problem's rubric and state the score plainly ("That earns 20 of 24"). Judge MEANING, not wording.
• Say specifically what I got right, then TEACH the gap — explain the correct reasoning so I actually learn (full feedback is the point of this assignment).
• OFFER A RE-ATTEMPT: "Want to raise your score? I'll give you a similar problem." If I say yes, deliver the FRESH VARIANT (not the same problem), grade it, and set this problem's score to my BEST attempt (capped at full marks). I can retry as many times as I want.
• Move on when I'm satisfied.
- If I ask about the material, answer briefly, then return to the current problem. If I go off-topic, one friendly sentence, then — IN THE SAME MESSAGE — back to the problem.
- Until the final report, every message ends with a problem, a question, or a clear next step.
- Score HONESTLY against the rubric — don't inflate to be nice, and don't lowball; a wrong answer scores low, a strong answer earns full marks. Grade only against the vetted key above. (Modeling honest evaluation is part of what this course teaches.)

COMPLETION + REPORT. After I've finished all four problems (and any re-attempts), produce the report in EXACTLY this format — the FIRST LINE is my score:
STUDENT'S SCORE: X/100
WEEK 1 ASSIGNMENT — Think Like an AI User
Student: [name] | Date: ___
Problem 1 (Vocabulary): a/24 — [one line]
Problem 2 (Fix weak prompts): b/26 — [one line]
Problem 3 (The mindset): c/24 — [one line]
Problem 4 (Fluency ≠ truth): d/26 — [one line]
Strongest skill: ___
Worth another look: ___
(The four problem scores must add up to the number on line 1.) Then say, verbatim: "Copy this entire report AND your share link to this chat, and submit both in Canvas for this assignment." End with one genuine sentence of encouragement.

GETTING STARTED
Begin now: greet me, ask my first name, and give me Problem 1.

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

Instructor grading note (Prof. Quinn)

• Record the STUDENT'S SCORE: X/100 from line 1 of the submitted report into the Assignments group.
• Spot-check a sample of chat share links against the reported scores; the embedded vetted key means the coach grades the same way for every student and every assistant, so checks are quick.
• The answer key + rubric live inside the student prompt (embed-don't-trust), so the score is consistent across ChatGPT / Claude / Gemini / Copilot. Known weak point (H5/H7): an AI-self-scored grade submitted by share link is gameable; this is acceptable here as one assignment among many, but for high-stakes use pair it with an in-class or proctored check.

Canvas placement block

canvas_object    = Assignment
title            = "Week 1 Assignment — Think Like an AI User (adaptive)"
assignment_group = "Assignments"
points_possible  = 100
grading_type     = points
assignment_type  = adaptive
submission_types = [online_text_entry, online_url]   # paste the report (score on line 1) + the chat share link
due_offset_days  = 6
published        = true
provenance       = "~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com"

Traditional variant — for comparison. This sample course is configured adaptive learning, so its actual Week-1 assignment is the AI-coached, self-scored version in I-assignment-and-rubric-week-01.md. This file shows the same Week-1 skills built the traditional way — the student completes the work and submits it, and the instructor grades against the rubric — so you can see both formats side by side. (Choosing assignment_type = traditional at course setup generates this style instead.)

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective assessed: Objective 1 (what genAI is; the terminology; the mindset; fluency ≠ truth) · SLO A (get quality results through good prompting) · SLO B (use AI critically)
Worth 100 points · Assignments group = 15% of the grade

The Assignment

Week 1 is about getting the right picture of what AI is and the mindset to use it well. In four short parts, you'll get the vocabulary straight, fix weak prompts, explain the working mindset, and show you understand that fluent output isn't automatically true. Submit your answers as a document upload or text entry in Canvas. You'll be graded on the rubric below — read it before you start.

Part 1 — Get the vocabulary right (24 pts). In one sentence each, define and distinguish (a) artificial intelligence (AI), (b) generative AI, (c) large language model (LLM), and (d) AGI. Then answer: when you open ChatGPT, is the app you're using "the model," or is the model something inside it?

Part 2 — Fix two weak prompts (26 pts). Improve each weak prompt by adding context, a clear goal, and at least one constraint or output format (don't just make it longer — make it genuinely more useful): (a) "help me with my resume"; (b) "give me ideas."

Part 3 — Explain the mindset (24 pts). (a) In your own words, explain the "general → specific, then iterate" mindset and why the first AI answer should be treated as a draft. (b) Explain what "the machine has no brain — use your own" means in practice — what is the human's job?

Part 4 — Fluency is not truth (26 pts). An AI gives you this confident answer to "Tell me about Silver Oak University": "Silver Oak University, founded in 1887 in Sacramento, is famous for its Nobel-winning chemistry department and its 42,000 students." (a) Why should you not trust this just because it's fluent and specific? (b) List two specific claims you'd verify and how you'd check each. (c) Name the general lesson this illustrates about AI output.

Integrity & AI note. This is your own work, submitted for grading. You may use an approved assistant (ChatGPT, Claude, Gemini, or Copilot) to help you think — but submitting AI-generated answers as your own is not the assignment; if AI helped you think, add a one-line note of which tool and how. (Note: this is the traditional format. In this course's actual adaptive assignment, you work the problems with the assistant and submit its self-scored report — see I-assignment-and-rubric-week-01.md.)

Rubric — 100 points

Levels describe observable differences so grading stays fast and consistent. (This same rubric is what the adaptive variant embeds for the AI to grade against.) Part totals: 24 + 26 + 24 + 26 = 100.

Instructor answer key — REMOVE BEFORE PUBLISHING TO STUDENTS

• Part 1: (a) AI = the broad field of computers doing tasks that used to need human intelligence (umbrella). (b) Generative AI = the slice that creates new content (text/images/audio/code). (c) LLM = the text-prediction engine inside a chatbot. (d) AGI = hypothetical future AI able to do any human intellectual task — does not exist today. Follow-up: the chatbot/app is not "the model"; the LLM is the engine inside it.
• Part 2: strong fixes name role/context + goal + a constraint or format. E.g., (a) "I'm a sophomore bio major applying for a lab internship; rewrite this resume bullet [paste] to emphasize lab skills, one line, strong action verbs." (b) "Give me 5 one-sentence activity ideas for a 20-minute study group on photosynthesis, ranked by how active they keep the group." (Adding length without context earns little credit.)
• Part 3: (a) start good-enough, then steer/iterate; the first answer is a draft, and value is in the back-and-forth. (b) the model predicts text, doesn't know, so the human sets the goal, judges, and verifies — AI drafts; you direct and decide.
• Part 4: (a) an LLM generates plausible text, so confident, specific details (dates, numbers, awards) are exactly what it fabricates — fluency/specificity ≠ truth. (b) any two checkable claims (founding year/location, 42,000 students, "Nobel-winning department") verified against the official site, a reliable reference, or a second tool. (c) fluency ≠ truth / "confidently wrong" → always verify specific facts, numbers, and citations. (Note: the "facts" in this prompt are intentionally fabricated — Silver Oak University is fictional — which is the whole point.)

Canvas placement block

canvas_object    = Assignment
title            = "Week 1 Assignment — Think Like an AI User (traditional)"
assignment_group = "Assignments"
points_possible  = 100
grading_type     = points
assignment_type  = traditional
submission_types = [online_upload, online_text_entry]
due_offset_days  = 6
published        = true
rubric_ref       = "week-01-assignment-rubric"
provenance       = "~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com"