Week 4 — Discussion (Adaptive Learning) · "Formula or Cage? / Diagnose the Bloated Prompt"

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective: Objective 2 (structured prompting; meta-prompting; when frameworks help vs. hinder) · SLO B (reason critically about AI practices)
This is Discussion 4 of 15 · Discussions group = 10% of the grade · Worth 20 points
Format: adaptive learning — instead of writing a post cold, you'll think it through in a real-time dialogue with your own AI, then post the short summary the AI writes with you (plus a link to your chat).

Part 1 — Student Instructions (read this first)

What this is. You'll take a stance on a genuinely arguable question — does a rigid prompt formula help you or limit you? — and then diagnose a bloated, contradictory prompt — identify what's wrong with it and how to fix it — in a back-and-forth conversation with an AI assistant. The AI's job is to draw out and challenge your thinking — it will not hand you the answer. When you've reasoned it through, it produces a short summary you post to the class.

How to run it (about 15–20 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. Have the conversation. Answer honestly and push back — the better you engage, the better your summary.

What to submit. When the AI gives you the DISCUSSION SUMMARY, copy it and your conversation's share link, and post both to the Week 4 discussion board as your initial post by Friday, Sep 25. Then reply to two classmates by Sunday, Sep 27 — engage with their verdict on the formula question and their diagnosis of the prompt.

Integrity note. The dialogue and the analysis are yours; the posted summary must reflect your reasoning, in your own words.

Part 2 — The Discussion-Partner Prompt (copy everything in the box)

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

You are my discussion partner for Week 4 of "Using Artificial Intelligence" (AI 101) at Silver Oak University. We are going to have a real back-and-forth about whether rigid prompt formulas help or limit thinking and about diagnosing a bloated, contradictory prompt. Your job is to draw out and challenge MY thinking through conversation — not to lecture me, and never to write my discussion post for me.

THE TWO THINGS WE'RE DEBATING

1. Formula or cage? The nine-component structured-prompt framework (Context · Role · Goal · Audience · Constraints · Voice/Format · Data/Logic · Examples · Evaluation) gives every prompt a systematic scaffold. But some people argue that rigid formulas get in the way: they slow you down, they force structure where a simple conversation would work, and they can turn prompting into bureaucratic box-checking instead of creative thinking. Using Week 4 ideas, I have to take a position — does the framework help more than it hinders, does it hinder more than it helps, or does the answer depend on the situation — and defend it with specific reasoning.

2. Diagnose the bloated prompt. Here is a real-sounding prompt that has multiple problems. I have to name at least two specific problems and say how I'd fix them:

"You are a world-renowned expert in productivity, behavioral psychology, and executive communications with 30 years of experience running Fortune 500 C-suite communications for technology firms. Your writing style is precise, data-driven, warm-but-authoritative, slightly informal, never using passive voice, always using Oxford commas, referencing specific studies where possible, and ensuring that every sentence adds real value. Write a 150–200-word update email, but only if you can confirm the accuracy of all claims first, and also make sure to check that the tone matches the organization's brand guide (attached — do not invent a brand guide), and ask for clarification on any ambiguous points before you write, and also include a subject line, and add a P.S. if appropriate, and avoid the word 'ensure.'"

WHAT WE'RE EXPLORING (use privately to steer — do NOT read to me as a checklist):
1. Specific situations where the nine-component framework clearly helps (recurring templates, high-stakes outputs, teaching someone to prompt) vs. situations where it's overkill (short one-off tasks, conversational exchanges).
2. My reasoned position, supported by at least one concrete example from my own experience or the course.
3. In the bloated prompt: the over-specified Role; the contradictory instructions ("ask for clarification" vs. "write now"); the impossible requirement ("only if you can confirm accuracy"); the cosmetic micro-constraint ("avoid the word 'ensure'"); the missing brand guide it references.
4. A lean, fixed version of the prompt that preserves what's valuable and cuts what isn't.
5. The underlying principle: add a component only when it changes the output. If removing it doesn't change anything, remove it.

HOW TO RUN THE DIALOGUE
- Open by greeting me warmly (2–3 sentences), asking my FIRST NAME, and asking ONE question that gets me to take a first position on whether the framework helps or hinders. (If I never give my name, keep going, but ask before the summary.)
- Exactly ONE question per message, then stop and wait. Never stack questions.
- Build on MY words: quote or paraphrase what I said, then go deeper.
- Introduce at least one counterpoint (e.g., "but doesn't a checklist also force you to think through things you'd skip?"; "isn't the real problem not the framework but how rigidly it's applied?") so I have to defend or revise my view — respectfully.
- Move me from the formula question to the bloated-prompt diagnosis once I've taken a real position on the first.
- Keep YOUR messages short; I should be doing most of the thinking and talking.

ENGAGEMENT GUARDS
- Don't accept a one-word or low-effort answer — gently probe for the reasoning.
- Don't lecture, and don't hand me my position or sentences I can paste as my post.
- If I go off-topic, give a brief friendly answer (a sentence or two) and then, IN THE SAME MESSAGE, steer us back.
- Until the summary, EVERY message must end with a question or a clear prompt to continue.
- Present both sides of the formula question evenhandedly — don't lead me to a single "right" verdict.

THE EXIT CONDITION
After at least 5 substantive exchanges AND once I have (a) taken and defended a clear position on the formula question with at least one concrete example, (b) identified at least two specific problems in the bloated prompt and named a fix for each, (c) articulated the principle behind the diagnosis (add a component only when it changes the output), and (d) engaged with at least one counterpoint — whichever happens LAST — tell me we've had a good discussion and you'll summarize. Don't stop earlier; don't drag well past it.

THE DISCUSSION SUMMARY — produce it in EXACTLY this format, drawn ONLY from what I actually said (never invent a position I didn't take):
WEEK 4 DISCUSSION SUMMARY — Formula or Cage? / Diagnose the Bloated Prompt
Student: [name] | Date: ___
My verdict on the formula question (and why, with a concrete example): ___
A counterpoint I weighed: ___
Problems I found in the bloated prompt: ___
My fix (the lean version): ___
The underlying principle I used: ___
Then say, verbatim: "Copy this summary AND your share link to this chat, and post both to the Week 4 discussion board as your initial post — then reply to two classmates." End with one genuine sentence about something I reasoned well.

GETTING STARTED
Begin now: greet me, ask my first name, and ask your opening question.

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

Participation rubric (instructor) — 20 points

Grading note (Prof. Quinn): the posted artifact is the AI-written summary + the chat share link. A glowing summary from a one-line chat is the failure mode — the rubric rewards the dialogue, not the AI's prose. The formula-vs-cage question has no single correct answer; reward genuine reasoning from either direction.

Canvas placement block

canvas_object    = DiscussionTopic
title            = "Week 4 Discussion — Formula or Cage? / Diagnose the Bloated Prompt (adaptive)"
assignment_group = "Discussions"
points_possible  = 20
grading_type     = points
discussion_type  = adaptive
due_offset_days  = 4     # initial post (AI summary + chat share link) — Fri Sep 25
reply_offset_days = 6    # two peer replies — Sun Sep 27
published        = true
submission_note  = "Initial post = the AI discussion summary + the chat share link; then reply to two classmates."
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-4 discussion is the BYOAI-dialogue version in G-discussion-week-04.md. This file shows the same Week-4 topic built the traditional way — an instructor-posted prompt where students write their own post and reply to peers — so you can see both formats side by side. (Choosing discussion_type = traditional at course setup generates this style instead.)

Course: Using Artificial Intelligence (AI 101) · Silver Oak University (fictional sample) · Prof. Quinn
Objective: Objective 2 (structured prompting; meta-prompting; when frameworks help vs. hinder) · SLO B (reason critically about AI practices)
Discussion 4 of 15 · Discussions group = 10% of the grade · Worth 20 points

The Discussion

This week gave you a nine-component framework for building prompts systematically — and a technique (meta-prompting) for letting the AI help write the prompt. Now let's debate whether that framework is a tool or a trap, and practice diagnosing one that's gone wrong.

Your initial post (by Friday, Sep 25 — about 150–200 words). Answer both parts:

• Part 1 — Formula or cage? The nine-component structured-prompt framework (Context · Role · Goal · Audience · Constraints · Voice/Format · Data/Logic · Examples · Evaluation) gives every prompt a systematic scaffold. But some people argue that rigid formulas slow you down, force unnecessary structure, and turn prompting into box-checking instead of thinking. Take a clear position — the framework helps more than it hinders, it hinders more than it helps, or the answer depends on the situation — and defend it using at least one specific example (from your own experience this week or from the lecture). Address the strongest version of the opposing view.

• Part 2 — Diagnose the bloated prompt. Here is a prompt with problems. Name at least two specific issues and describe how you'd fix them:

"You are a world-renowned expert in productivity, behavioral psychology, and executive communications with 30 years of experience running Fortune 500 C-suite communications for technology firms. Write a 150–200-word update email, but only if you can confirm the accuracy of all claims first, and also check that the tone matches the organization's brand guide (attached — do not invent a brand guide), and ask for clarification on any ambiguous points before you write, and also include a subject line, and add a P.S. if appropriate, and avoid the word 'ensure.'"

Replies (by Sunday, Sep 27). Reply to at least two classmates. Don't just agree — challenge their verdict on the formula question with an angle they didn't use, or identify a different problem in the bloated prompt, or offer a leaner fix than theirs.

What a strong post looks like: "My position is that the framework helps most for recurring, high-stakes templates — I used it in Studio 4 and caught two gaps I'd never have named without it. For quick one-off tasks, it's overkill. The opposing view has real merit: when you follow all nine components for a simple question, the prompt becomes a bureaucratic form. The middle position: use the framework as a checklist, not a required essay. On the bloated prompt: two problems I see are the contradictory instructions ('confirm accuracy first' + 'write now' — the AI can't do both) and the over-specified Role (30 years in Fortune 500 C-suite executive communications is a lot of preamble for a 150-word update email — it adds length without changing the output). Fix: cut the Role to one sentence, drop the impossible accuracy-confirmation instruction, and add the brand guide if you have one."

Why this matters: the ability to look at a prompt and diagnose what's wrong — and fix it without starting over — is the highest-leverage prompting skill. Most students learn it by building and testing; this discussion is the diagnostic pass.

Integrity & AI note. Write your post in your own words — that's the exercise. You may use an approved assistant to help you brainstorm or check an idea, but the post you submit must be your own thinking; if AI helped, add a one-line note. (Note: this is the traditional format. In this course's actual adaptive discussion, working through the verdict and the diagnosis with the assistant is the activity — see G-discussion-week-04.md.)

Participation rubric — 20 points

Grading note (Prof. Quinn): the formula-vs-cage question has no single correct answer; reward genuine reasoning from either direction. The bloated-prompt diagnosis has clearer right answers — watch for students who identify only surface-level issues (word count) while missing the structural contradictions.

Canvas placement block

canvas_object    = DiscussionTopic
title            = "Week 4 Discussion — Formula or Cage? / Diagnose the Bloated Prompt (traditional)"
assignment_group = "Discussions"
points_possible  = 20
grading_type     = points
discussion_type  = traditional
due_offset_days  = 4     # initial post — Fri Sep 25
reply_offset_days = 6    # two peer replies — Sun Sep 27
published        = true
submission_note  = "Students write an original initial post and reply to two classmates in the Canvas discussion."
provenance       = "~ Prof. Quinn's edition · Fall 2026 · built with thecoursemaker.com"