Week 3 — Readings & Resources · Prompting I — Conversation, Content & Emphasis

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective covered: Objective 2 — Construct effective AI prompts using conversation, content-provision, and emphasis techniques.

How to use this page

Everything here is a link to an external resource — open it in your browser, the same way you'd open any link. Nothing needs to be downloaded.

This week's load is deliberately light: 2 short readings + 2 short videos, grouped by the ideas from the lecture, plus a quick reference on Markdown formatting. Watch or read one item per group and you're ready for the quiz; do all of them and you'll be comfortable with every angle. Total time is roughly 30–40 minutes if you do everything, less if you pick one per group.

Order that matches the lecture: ① the directed conversation → ② sycophancy → ③ emphasis & formatting → ④ privacy preview.

A habit to carry forward: before trusting any reading — even a linked article — ask the verification questions: Is this generated or curated? Who published it and why? How would I check the main claim?

① Directed Conversation & Asking for Guidance

Maps to Lecture Segment 2. A productive AI conversation has five moves — goal, guidance, read, steer, close. Practicing this pattern is the whole week.

Reading — "Prompting guide 101" (Anthropic)
🔗 https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
Why it earns the click: Anthropic's own prompt-engineering overview covers the basics of giving context, asking follow-ups, and structuring a productive conversation — directly relevant to Skill 1. Skim the intro section and the "be specific" and "iterative refinement" topics.
⏱ ~10 min (selective read)

Video — "ChatGPT Tutorial: How to have a Better Conversation" (Skill Leap AI, YouTube)
🔗 https://www.youtube.com/watch?v=JTFFAMqN-nQ
Why it earns the click: a practical walkthrough of the conversation-style prompting moves we covered in class — short, practical, and demonstrates the pattern on a real task.
⏱ ~8 min

② Sycophancy — The Agreement Trap

Maps to Lecture Segment 3. AI tools tend to agree with users — this is well-documented and worth understanding. These resources give you the plain-language explanation and the evidence base.

Reading — "Claude's character" (Anthropic)
🔗 https://www.anthropic.com/news/claude-character
Why it's assigned: Anthropic's own page on Claude's character acknowledges the challenge of honesty vs. validation — the background for why sycophancy is a known issue and something Anthropic actively works to reduce. Read the "Honesty" section. Brief but authoritative.
⏱ ~5 min

Reading — "What is AI sycophancy, and why does it matter?" — look this up in your preferred search engine or news source. (Search: "AI sycophancy explained" or "why AI agrees with users.")
Why it's here: sycophancy has been covered in accessible journalism and blog posts — a quick search will surface recent readable explainers. Reading one gives you the plain-language evidence base for class. (Note: the brief rules apply — verify the outlet is credible and don't treat any one source as definitive.)
⏱ ~5 min

Note on this topic: sycophancy in AI systems is well-documented in Anthropic's research and published work — the phenomenon is real and openly acknowledged by AI developers. The class discussion summarizes the key practical facts.

③ Emphasis — Markdown, Tags, and Formatting

Maps to Lecture Segment 6. Markdown headings, bold, XML-style tags, and capitalization are the structural signals that help the AI understand what's important and what format you want.

Video — "Markdown in 100 Seconds" (Fireship, YouTube)
🔗 https://www.youtube.com/watch?v=HUBNt18RFbo
Why it earns the click: a 2-minute primer on Markdown syntax — the headings, bold, bullets, and code fences that you'll use in your prompts this week. Fast and sufficient for what Week 3 requires.
⏱ ~2 min

Reference — "Markdown Guide" (official reference)
🔗 https://www.markdownguide.org/basic-syntax/
Why it's here: the authoritative, always-available Markdown syntax reference. Bookmark this — you'll use Markdown all term. Skim the Basic Syntax section; you don't need the extended syntax for Week 3.
⏱ ~5 min (skim)

④ Privacy Preview — What Not to Paste

Maps to Lecture Segment 5 + Segment 7. This is a preview of the full privacy unit in Week 15. For now: the billboard test applies before you paste anything into a free tool.

Reading — "Privacy Policy" and "Terms of Service" — your current AI tool
🔗 ChatGPT: https://openai.com/policies/privacy-policy
🔗 Claude: https://www.anthropic.com/legal/privacy
🔗 Gemini: https://policies.google.com/privacy
🔗 Copilot: https://privacy.microsoft.com/en-us/privacystatement
Why it's assigned: you're using at least one of these tools every week — this week spend five minutes skimming the data-use section of whichever tool you're using. What does it say about whether your conversations are stored? What controls exist? You don't need to memorize it; you need to know it exists and where to find it. (Full analysis in Week 15.)
⏱ ~5 min (selective read — just the data-use / conversation-storage section)

Pick-one quick path (≈12 min total)

In a hurry? Do exactly these two and you'll be ready for the quiz:
1. Watch "Markdown in 100 Seconds" (group ③) — 2 minutes.
2. Read the Anthropic prompt-engineering overview intro (group ①) — ~10 min skim.

Heads-up (links rot): these point to outside sites that occasionally move or rename pages. If a link ever fails, tell Prof. Quinn and use the official docs above in the meantime. Nothing here is downloaded or redistributed — all resources stay as links to their original sources. The Anthropic links in particular are official product documentation and should be stable.