Back to the Using Artificial Intelligence outline The Course Maker
Using Artificial Intelligence outline
Week 3 · Module overview

Week 3 — Module Framing · Prompting I — Conversation, Content & Emphasis

Using Artificial Intelligence · AI 101 Fall 2026 · Prof. Quinn Fictional sample

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Module: Week 3 of 16 · Fall 2026 · in-person, two 75-minute sessions
Objective covered: Objective 2 — Construct effective AI prompts using conversation, content-provision, and emphasis techniques.

This file holds two pieces: (A) the Module 3 Overview page ("Start Here") and (B) the Welcome Announcement that drips out when the module opens. Dates below assume a Tuesday/Thursday lecture pattern with Week 3 meeting Tue Sep 15 and Thu Sep 17, and end-of-week work due Sunday Sep 20, 11:59 p.m. Adjust the day-of-week and times to match your section.


(A) Module 3 Overview — Start Here

Welcome to Week 3: Talking to AI — and Making It Listen

This is your home base for the week. Read it first, then work the checklist below from top to bottom. Everything you need is linked inside the module. Bring your laptop to class — we build and test things live.

Two weeks in, you know what AI is and why it can be confidently wrong. Now we go hands-on with how to actually run a productive conversation — including the tricky part: what happens when the AI just agrees with everything you say. This week introduces three skills that will serve you every time you open a chatbot:

  • Skill 1 — Have a real conversation. Ask for guidance, push back, and learn to spot when the AI is sycophantic (agreeing with you when it shouldn't).
  • Skill 2 — Provide content. Paste in a document, your notes, or another input and direct a transformation. Understand what stays inside the AI's context window — and what you should not paste into a free tool.
  • Skill 3 — Use emphasis. Control what the AI pays attention to with Markdown headings, XML-style tags, and CAPITALIZATION for must-dos.

The course's running theme — use AI well, then verify its work — runs straight through this week: we'll practice catching sycophancy, checking what the AI changed versus invented when you paste your content, and using emphasis to make its output more useful (and more auditable).

The week's big question

"You've given the AI something to work with — how do you make sure it actually does what you asked?"

By Sunday you'll be able to run a directed conversation, paste content and direct a transformation using emphasis, and catch where the AI misread or invented — instead of just accepting whatever comes back.

By the end of this week, you can…

Use this as a checklist. If you can do all five out loud, you're ready for the quiz.

  • [ ] Have a directed conversation — set a goal, ask for guidance, follow up, and know when you're done.
  • [ ] Counter sycophancy — recognize when the AI is just agreeing with you and use techniques to get an honest response.
  • [ ] Provide content — paste a document or notes and direct the AI to summarize, extract, or rewrite it.
  • [ ] Explain the context-window tradeoff — why very long pastes can cause the AI to drop earlier information.
  • [ ] Use emphasis — Markdown headings/bold, XML-style tags, and CAPS to tell the AI what matters most and what format to use.

What's due this week, and when

Work these in order — each one gets you ready for the next.

# Do this Type Due
1 Read the week's readings + watch the linked videos Read / watch (ungraded prep) Before Thu Sep 17
2 Skim the slides (Deck 3) and the Week 3 lecture outline Prep (ungraded) Alongside class
3 Lecture Tutorial 3 — work through conversation, content, and emphasis with one approved assistant (ChatGPT, Claude, Gemini, or Copilot), then submit the conversation share link Lecture Tutorial · graded (5% group) Sun Sep 20, 11:59 p.m.
4 Practice exercises — low-stakes reps to lock in the ideas Practice · ungraded Sun Sep 20 (recommended)
5 AI Build Studio 3 — "Provide-Content Prompting" — paste a real document and direct a transformation using emphasis; catch what the AI misread or invented Studio · graded (AI Build Studios, 15% group) · 50 pts Sun Sep 20, 11:59 p.m.
6 Quiz 3 — covers conversation, sycophancy, content-provision, emphasis, and privacy (no AI on quizzes) Quiz · graded (Quizzes, 10% group) Sun Sep 20, 11:59 p.m.
7 Discussion 3 — "Where's the Line? / Sycophancy in the Wild" — reason through the content-privacy question and analyze a sycophantic exchange Discussion · graded (Discussions, 10% group) Initial post Fri Sep 18; replies Sun Sep 20
8 Assignment 3 — "Direct the Machine" — rewrite prompts using emphasis; complete provide-content tasks; spot and counter sycophancy, coached and scored by one approved assistant Assignment · graded (Assignments, 15% group) · 100 pts Sun Sep 20, 11:59 p.m.

The usual AI policy reminder: you're required to use AI on the tutorial, discussion, assignment, practice, and Studio — that's the point of this course. AI is not allowed on the quiz, which checks that you understand. And every week you deliberately catch the AI's mistakes — this week's Studio puts that front and center.

Late policy reminder: 10% off per day late. If life happens, reach out before the deadline.

How to succeed this week

  • Try sycophancy on purpose. Pick any claim — even a wrong one — tell the AI it's true, and see how it responds. Most of the time it'll agree. That's the lesson. Then ask it, "Are you agreeing because you're certain, or because I said so?" and see what happens.
  • Use emphasis before you paste. Before dropping a long document in, add a Markdown heading or a simple tag like [SUMMARIZE THIS:] so the AI knows its job. You'll see the difference in the output quality.
  • Check what it changed vs. what it invented. When the AI summarizes your content, compare the original. Anything specific in the AI's version that wasn't in your source? Flag it — that's the verification skill.
  • Privacy first. This week previews a rule we'll deepen in Week 15: don't paste content you wouldn't post publicly. This week you'll use your own notes or a public document — nothing private.

You've got the fundamentals. This week you start driving.


(B) Welcome Announcement — Module 3

Release setting: post on the module's start day (offset = 14 days from course start), i.e., Tue Sep 15, 2026 — not before. If your platform won't preserve the scheduled date on import, post this as a draft labeled "Release: Tue Sep 15."

Subject: Week 3 — let's make the AI actually do what you asked 🎯

Hi everyone,

Quick question before class Tuesday: have you ever told an AI your idea and had it immediately say it was brilliant — no pushback, no caveats, just full agreement? That's called sycophancy, and it's one of the sneakiest failure modes these tools have. This week we name it, diagnose it, and learn to work around it.

Week 3 — Prompting I: Conversation, Content & Emphasis is where prompting gets practical. We go from "give the AI a one-liner and hope" to actually directing a conversation, handing it real content to work with, and using emphasis (Markdown headings, XML-style tags, and CAPS) to control what comes back.

A heads-up on the AI policy — still backwards from most classes:
1. You are required to use AI on the tutorial, discussion, assignment, practice, and Studio. But AI is not allowed on the quiz — that's your solo check.
2. This week's Studio has you paste real content into an assistant and catch what it misread or invented — that's the skill we're building.
3. Bring your laptop to both sessions — Tuesday we'll run the conversation and sycophancy demo live.

Three things not to miss this week:
1. Lecture Tutorial 3 — work through all three skills with an approved assistant and submit the share link. Due Sun Sep 20.
2. Studio 3, Quiz 3, Discussion 3, and Assignment 3 all close Sun Sep 20 — start the Studio early; it needs a real document.
3. Open the Start Here page first — it lays out everything in order with due dates.

By Friday, you'll have a reliable system for making the AI actually do what you ask — and you'll know exactly when to trust it and when to push back.

See you Tuesday,
Prof. Quinn


~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com