Week 6 — Readings & Resources · Simulations & Reusable Prompts

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective covered: Objective 2 — Apply effective prompting techniques, including simulations and reusable templates, to accomplish real-world tasks and critically evaluate AI output.

How to use this page

Everything here is a link to an external resource — open it in your browser. Nothing needs to be downloaded.

This week's load is deliberate: 2 short readings + 2 short videos, grouped by the ideas from the lecture, plus the AI tool homepages you already know. Watch or read one item per group and you're ready for Quiz 6; do all of them and you'll be very comfortable. Total time is roughly 30–40 minutes if you do everything, far less if you pick one per group.

Order that matches the lecture: ① what simulation prompts are and how they work → ② the pre-mortem technique → ③ AI-generated misinformation and the historical-figures risk → ④ your approved assistant tools.

The verification habit: before you run any simulation, ask yourself — is anything in the AI's output a specific factual claim I should be able to check? If yes, check it.

① Simulation Prompts — Role-play and Rehearsal

Maps to Lecture Segment 2. What a simulation prompt is; the four types; role, goal, and exit condition.

Video — "How to Use AI for Practice and Simulation" (by the OpenAI team, available on YouTube)
🔗 https://www.youtube.com/results?search_query=openai+chatgpt+roleplay+simulation+practice
Why it earns the click: search this phrase on YouTube and look for short (under 10 min) official or clearly-attributed demos showing how to structure a role-play prompt with a specific scenario. The official OpenAI YouTube channel publishes practical how-to videos. Verify the publisher before trusting the technique.
⏱ ~5–10 min

Reading — "Prompt engineering: Role prompting" (Anthropic, Claude docs)
🔗 https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/use-examples
Why it's assigned: Anthropic's own prompt-engineering documentation explains how to give Claude (or any LLM) a specific role and what that changes about the output. Read the examples section for how specificity in the role prompt changes results. This is the authoritative source on the technique we are building this week.
⏱ ~10 min

② The Pre-Mortem — Failing Forward

Maps to Lecture Segment 2 (pre-mortem type) and Segment 7 (technology workflow). The pre-mortem is a real planning technique — here is where it comes from.

Reading — "Performing a Project Premortem" (Harvard Business Review)
🔗 https://hbr.org/2007/09/performing-a-project-premortem
Why it's assigned: this is the original article by psychologist Gary Klein introducing the pre-mortem technique — it is the real-world source of the method we are applying to AI simulation prompts. Reading the original gives you intellectual grounding for the Studio. (HBR articles may require a free account to read in full; the abstract is always free.)
⏱ ~8 min

③ AI-Generated Misinformation — The Historical-Figures Risk

Maps to Lecture Segment 3 — the most important concept of the week. AI-generated historical dialogue is not verified history.

Video — "AI Hallucinations and Fake Quotes" — search for a short explainer
🔗 https://www.youtube.com/results?search_query=AI+hallucination+fake+quotes+history+misinformation
Why it earns the click: search this phrase and look for a short (under 8 min) explainer from a reliable source (BBC, PBS, a university, or a major tech publication) on how AI generates plausible-sounding but fabricated historical quotes. This is the specific failure mode that makes the "never cite simulated dialogue as a real quote" rule load-bearing.
⏱ ~5–8 min

Reading — "Generative AI and historical misinformation" — search for a current piece
🔗 https://www.google.com/search?q=generative+AI+historical+figures+misinformation+fake+quotes+site:bbc.com+OR+site:theguardian.com+OR+site:nytimes.com
Why it's here: a current news article (BBC, The Guardian, or New York Times are reliable starting points) on how AI-generated historical dialogue has been misused or spread as misinformation. The specific article will vary by semester — search the phrase above and find a piece published in the past two years. Read the introduction and the examples section.
⏱ ~8 min

④ The Approved Tool Homepages (pick the one you already use)

You only need one approved assistant for this week's tutorial, practice, discussion, assignment, and Studio. These are the official product pages.

• ChatGPT (OpenAI) 🔗 https://chatgpt.com
• Claude (Anthropic) 🔗 https://claude.com
• Gemini (Google) 🔗 https://gemini.google.com
• Copilot (Microsoft) 🔗 https://copilot.microsoft.com

(Claude Cowork desktop — the automation platform for Weeks 11–14 — is not needed yet.)

Quick path (≈15 min total)

In a hurry? Do exactly these two and you'll be ready for Quiz 6:
1. Read the Anthropic prompt-engineering docs (group ①) — specifically the role and examples sections.
2. Read the HBR pre-mortem article (group ②) — skim the intro and the three-step method.

Heads-up (links rot): the HBR link above points to the original 2007 article and has been stable for years. The YouTube and Google search links will always surface current results. If any direct link ever fails, tell Prof. Quinn and use the search terms above to find equivalent resources. Nothing here is downloaded or redistributed — all resources stay as links to their original sources.