Week 6 Quiz — Simulations & Reusable Prompts

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Covers: simulation types · role, goal, and exit condition · generated vs. verified historical dialogue · reusable prompt templates · catching fabrications in a simulation output
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-06-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 6 ideas.

---

Questions, key, and feedback

Q1 (MC). Which best describes what an AI simulation prompt does?
- A. It searches the internet for real-world examples of the scenario
- B. It sets up a role-play scenario where the AI acts as a character or adopts a perspective so you can practice or explore a situation ✅
- C. It records a real-world conversation and replays it back accurately
- D. It generates a prediction about what will actually happen in the future

Feedback: A simulation gives the AI a role and a goal and puts you in a scenario to rehearse or explore — it is not a search (A), a recorder (C), or a forecast (D).

---

Q2 (Matching). Match each simulation type to its primary use case.

Simulation type	Primary use case
Difficult-customer simulation	Practice handling complaints or conflict before a real interaction
Pre-mortem simulation	Imagine a project has already failed and work backward to find the cause
Decision role-play simulation	Hear multiple stakeholder perspectives to stress-test a plan
Adaptive-tutor simulation	Get personalized teaching at your own pace on a specific topic

Feedback: Each type has a distinct goal: difficult-customer = rehearse conflict; pre-mortem = fail first, fix before you start; decision role-play = stress-test from multiple angles; adaptive tutor = learn at your own pace with feedback.

---

Q3 (MC). A student runs a simulation where the AI role-plays as Abraham Lincoln and "quotes" him saying, "The internet will one day connect all free peoples." What is the most important thing to understand about this quote?
- A. It is a real historical quote that Lincoln said in a private letter
- B. It is a generated line of text — the AI invented it; it is not a verified historical record and must never be cited as real ✅
- C. It is accurate because the AI was trained on historical documents
- D. It is accurate as long as the overall topic is historically plausible

Feedback: Every word the AI puts in a historical figure's mouth is generated, not transcribed. Training on historical text means the AI can imitate style; it does not make the specific generated words historically verified. This "quote" does not appear in any real historical record and must never be cited as one.

---

Q4 (True/False). True or False: If an AI simulation of a job interview says you performed well, that is a reliable prediction that you will succeed in the real interview.
- False ✅

Feedback: False. A simulation is a rehearsal space, not a crystal ball. The AI produces a plausible-text scenario — it is not running a model of the real world or predicting actual outcomes. Use simulation performance as practice feedback, not as a forecast.

---

Q5 (MC). What is the core advantage of building a personal reusable prompt library?
- A. The AI stores your prompts on its servers so they never need to be re-typed
- B. You write a well-crafted prompt once and can apply it to many similar tasks without starting from scratch each time ✅
- C. A saved prompt becomes more accurate over time as the AI learns it
- D. Reusable prompts are the only type the AI can understand

Feedback: A reusable prompt is a template you control — saved in your own notes, with placeholder variables you fill in each use. The AI does not store or learn from your prompts between sessions. The value is the time you save, not any AI learning effect.

---

Q6 (MC). A student prompts: "Pretend you are a job interviewer." The AI asks generic questions that don't match the student's field. Which revision best fixes this?
- A. Add "please" to make the AI more cooperative
- B. Repeat the same prompt three more times
- C. Specify the role, company type, job title, and the type of interview (behavioral vs. technical), e.g., "Act as a hiring manager at a nonprofit conducting a behavioral interview for a marketing coordinator role" ✅
- D. Ask the AI to search the internet for real interview questions

Feedback: This is a specificity fix. "Pretend you are a job interviewer" gives the AI almost nothing to work with. Adding the specific company type, role, and interview style changes the output from generic to genuinely rehearsal-ready. Politeness (A), repetition (B), and asking the AI to "search" (D) don't address the actual problem.

---

Q7 (Multiple answer — select all that apply). Which of the following are legitimate, educationally sound uses of an AI simulation? Select all that apply.
- A. Practicing how to respond to a difficult colleague before a hard conversation ✅
- B. Citing an AI-generated "quote" from a historical figure in a research paper as a real source
- C. Running a pre-mortem to identify weaknesses in a project plan ✅
- D. Getting coaching from an AI acting as an adaptive tutor on a concept you're studying ✅
- E. Using the simulation's fictional outcome as a verified fact about the real world

Feedback: Legitimate uses: A (difficult-conversation rehearsal), C (pre-mortem risk identification), D (adaptive tutoring). B is wrong — AI-generated historical dialogue is generated, not verified, and must never be cited as a real source. E is wrong — a simulation's outcome is generated text, not a verified real-world fact.

---

Q8 (MC). In a pre-mortem simulation, what does the AI help you do?
- A. Celebrate everything that went right in your project
- B. Predict the exact future outcome of your plan with high accuracy
- C. Imagine the project has already failed and reason backward to surface potential problems before they happen ✅
- D. Find a real historical example of a project identical to yours

Feedback: The pre-mortem (a technique from planning research) works by imagining failure first and then reasoning backward — which is more effective at surfacing risks than brainstorming "what might go wrong" forward. It is a reasoning exercise (C), not a celebration (A), a forecast (B), or a historical search (D).

---

Q9 (MC). Which element is MOST important to include in a reusable prompt template to make it easy to apply to many different situations?
- A. A specific date and time stamp so the AI knows when you wrote it
- B. Clear placeholder variables (e.g., [TOPIC], [AUDIENCE], [LENGTH]) that you fill in each time ✅
- C. A list of every previous topic you have ever discussed with the AI
- D. The word "reusable" in the first line so the AI treats it differently

Feedback: Placeholder variables are the innovation that turns a one-off prompt into a reusable tool. They mark exactly what changes for each new use. Dates (A) don't affect reusability; prior topic lists (C) don't help the AI across sessions; and the word "reusable" (D) has no special meaning to the AI.

---

Q10 (True/False). True or False: When an AI role-plays a conversation between two historical figures, the dialogue it generates is drawn directly from verified historical records and can be cited as accurate.
- False ✅

Feedback: False. AI-generated historical dialogue is generated, not transcribed. The AI interpolates in the style of historical figures based on training patterns — but those specific words never appeared in any verified historical record. Such dialogue may be useful for thinking about historical context, but it must never be presented or cited as accurate history.

---

Answer key (quick reference)

Q	Answer	Q	Answer
1	B (role-play scenario for practice)	6	C (specify role, company, job, interview type)
2	Matching: difficult-customer→conflict practice / pre-mortem→fail-backward / decision role-play→stress-test / adaptive tutor→personalized learning	7	A, C, D
3	B (generated text, not verified — never cite as real)	8	C (imagine failure, reason backward)
4	False (rehearsal, not prediction)	9	B (placeholder variables)
5	B (write once, reuse with blanks)	10	False (generated, not from verified records)

---

Blueprint & item-bank note

#	Type	Concept	Objective
1	MC	What a simulation prompt is	2
2	Matching	Simulation type → use case	2
3	MC	AI-generated historical quotes are not verified (the critical rule)	2
4	True/False	Simulation outcome ≠ real prediction	2
5	MC	Reusable prompt library benefit	2
6	MC	"What's the prompting fix?" — specificity in a role prompt	2
7	Multiple answer	Legitimate vs. illegitimate simulation uses	2
8	MC	Pre-mortem definition and purpose	2
9	MC	Placeholder variables in a reusable template	2
10	True/False	Historical-figure dialogue is generated, not verified	2

All 10 items are tagged course=AI101 · week=6 · objective=2 and deposited into the item bank. Distractors target the week's classic misconceptions: simulation outcome = real prediction; AI-trained-on-history = historically accurate; vague role = good enough; placeholder variable meaning; reusable prompt as a stored AI memory.

Quality gate (self-checked)

• Structure: 10 items, 1 point each; types = 6 multiple-choice + 1 matching + 1 multiple-answer + 2 true/false.
• Single-answer integrity: every MC and every true/false item has exactly one correct option; the matching item pairs one-to-one; the multiple-answer item keys A, C, D (requiring B and E to be left unselected).
• Critical-rule coverage: Q3 and Q10 directly test the generated-vs-verified rule for historical figures — both required by the week spec.
• Matching item: Q2 covers simulation type → use case, satisfying the ≥1 matching requirement.
• Prompting-fix item: Q6 is a scenario-based "what's the fix?" item, satisfying the ≥1 prompting-fix requirement.
• Verification note: no fabricated tool features or statistics; all conceptual claims are accurate and consistent with the lecture, tutorial, and VERIFIED_FACTS.md. Simulation types and pre-mortem technique referenced accurately (Gary Klein's pre-mortem concept, published in HBR 2007).
• Product-accuracy gate: PASS. No invented tool features; no false claims about AI tool behavior; all product references are factual.

Canvas placement block

canvas_object    = Quizzes::Quiz
title            = "Week 6 Quiz — Simulations & Reusable Prompts"
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"