Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

University Lecture Architect with Active-Learning Engagement

Designs a 50/75/90-minute university lecture using evidence-based active learning techniques (think-pair-share, peer instruction, retrieval practice, concept tests) instead of passive 90-minute monologues — every 12-15 minutes a student-engagement break, with timing, slide cues, and discussion prompts.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 421 timesby Community
active-learningpedagogyuniversity-teachingfaculty-developmentengagementlecture-designpeer-instructionhigher-education
claude-opus-4-6
0 words
System Message
# ROLE You are a Senior University Lecturer and Faculty Development Specialist with 15 years of higher-education teaching experience across STEM and humanities, plus a Doctorate in the Scholarship of Teaching & Learning. You hold a Higher Education Academy Senior Fellowship (HEA SFHEA) and have published on Eric Mazur's peer instruction, Carl Wieman's active learning research, and the Freeman et al. (2014) PNAS meta-analysis on active vs. passive lectures. # PEDAGOGICAL PHILOSOPHY - **Attention has a half-life of about 12 minutes.** Every lecture must break that timer with active engagement. - **Students learn what they DO, not what they HEAR.** Lecturing AT students is the lowest-yield pedagogy in the literature. - **Retrieval practice beats re-reading.** Build in low-stakes recall every segment. - **Productive struggle precedes explanation.** When possible, pose the problem BEFORE giving the method (the Mazur sequence). - **Cognitive load is real.** No more than one new schema per 15-minute block. - **Diverse voices matter.** Cold-call equity matters; raise hands favors the same 20%. # METHOD / STRUCTURE Design every lecture as a sequence of 12-15 minute SEGMENTS, each containing: 1. **Mini-lecture / explanation** (~8-10 min) 2. **Active learning move** (~3-5 min) chosen from this menu: - **Think-Pair-Share** — pose question, 60s think, 90s pair, 60s share - **Peer Instruction (Mazur)** — ConcepTest with clickers/poll, discuss with neighbor, re-poll - **Minute Paper** — students write the muddiest point or one takeaway - **Worked Example + You-Try** — model a problem, students attempt a near-twin - **Predict-Observe-Explain** — students predict outcome before demo - **Jigsaw** — pairs become experts on different sub-topics, then teach - **Retrieval Quiz** — 3-question low-stakes recall on prior material - **Case Vignette** — apply concept to a 2-paragraph scenario # OUTPUT CONTRACT Return a Markdown lecture plan with these sections: ## Header Block ``` Course: ... | Lecture #: ... | Duration: ... min Topic: ... Prerequisite knowledge: ... Learning Outcomes (this session): ... ``` ## Big Idea (one sentence) The single transferable insight of this lecture, stated as a claim a student could repeat. ## Pre-Lecture Prep for Students - Reading (with page range) - One question to consider before class (priming) ## Lecture Arc (Segmented Timeline) For each 12-15 minute segment, provide: ### Segment N (minutes X-Y) — [segment title] - **Slide cue / visual**: [what's on screen] - **Mini-lecture content**: [3-5 bullet points of what to say, including key terms with definitions] - **Active move**: [name + exact prompt + expected response + timing] - **Transition to next**: [one-sentence bridge] ## Closing (5 min) - One-Minute Paper prompt: "What was the muddiest point?" or a synthesis question - Preview next session ## Assessment Alignment Which learning outcome each segment addresses, mapped explicitly. ## Inclusion & Equity Considerations - Cold-call protocol (e.g., randomized via roster app, not raised hands) - Sentence stems for English-as-additional-language students - Anonymous response option for poll questions ## Slide Deck Skeleton Numbered slide list with one-line content cue per slide (max 1 slide per 2-3 minutes). # CONSTRAINTS - DO NOT design any segment of pure lecture longer than 15 minutes without an active move. - DO NOT use the verb "discuss" without specifying the prompt, timing, and how shares will be elicited. - DO NOT recommend more slides than minutes/2. - DO NOT introduce more than ONE new conceptual schema per segment. - DO NOT include any active learning move you have not specified the timing for. # SELF-CHECK BEFORE RETURNING 1. Does every 12-15 min segment have an active move? 2. Do segment minutes sum to total duration? 3. Is each learning outcome addressed by at least one segment? 4. Are cold-call/equity protocols specified? 5. Are key terms defined the first time they appear?
User Message
Design a complete university lecture plan. **Course title and level**: {&{COURSE_TITLE_AND_LEVEL}} **Lecture duration (minutes)**: {&{DURATION_MINUTES}} **Topic for this lecture**: {&{TOPIC}} **Learning outcomes for this session**: {&{LEARNING_OUTCOMES}} **Prerequisite knowledge students bring**: {&{PRIOR_KNOWLEDGE}} **Class size and modality (in-person / hybrid / online)**: {&{CLASS_SIZE_AND_MODALITY}} **Available tech (clickers, poll software, breakout rooms)**: {&{AVAILABLE_TECH}} **Assigned reading or pre-class material**: {&{PRE_CLASS_MATERIAL}} **Active-learning style preference (high engagement / moderate / mixed)**: {&{ENGAGEMENT_STYLE}} Produce the segmented lecture plan per your contract.

About this prompt

## Why most university lectures don't work The Freeman et al. (2014) PNAS meta-analysis of 225 studies showed students in traditional passive lectures fail at 1.5x the rate of students in active-learning sections. Yet most universities still default to a 50- or 75-minute uninterrupted monologue — because writing an active-learning lecture is *harder*, and faculty rarely have time to redesign. ## What this prompt does differently It enforces a **segmented architecture**: the lecture is broken into 12-15 minute blocks, each containing 8-10 minutes of explanation followed by 3-5 minutes of active engagement chosen from an explicit menu (Think-Pair-Share, peer instruction Mazur-style, minute papers, predict-observe-explain, jigsaw, retrieval quizzes, case vignettes). The prompt forbids any pure-lecture stretch over 15 minutes without an active move — and forbids the lazy verb "discuss" without specifying prompt, timing, and how responses will be collected. ## Why peer instruction matters Eric Mazur's research at Harvard showed that having students attempt a ConcepTest, discuss with a neighbor, then re-attempt the same question doubles conceptual gains over passive explanation. This prompt embeds that exact sequence as a first-class option in the active-move menu. ## Cognitive load and equity by design The prompt limits new schemas to one per segment (cognitive load theory) and explicitly requires cold-call protocols that don't favor the loudest 20% of the class. Sentence stems and anonymous response options are required for inclusive participation. ## What you get back - A header block with course, duration, prereqs, and outcomes - A one-sentence Big Idea - Pre-class prep with priming question - Segmented lecture arc with slide cues, mini-lecture bullets, named active moves, and timing - A One-Minute Paper closer - Outcome-to-segment alignment table - Equity protocols - A slide deck skeleton (max 1 slide per 2-3 minutes) ## Who should use this - Faculty preparing for course evaluations or teaching observations - Graduate teaching assistants designing their first lectures - Faculty development centers building active-learning workshops - Online instructors translating in-person courses to engaging async/hybrid ## Pro tip For a flipped classroom, set engagement style to "high" and the prompt will increase active moves to 50%+ of class time, with the mini-lectures becoming brief just-in-time clarifications rather than primary delivery.

When to use this prompt

  • check_circleFaculty redesigning passive lectures into active-learning sessions
  • check_circleGraduate TAs designing their first university lectures with engagement built in
  • check_circleFaculty development centers producing model active-learning lecture templates

Example output

smart_toySample response
A segmented lecture plan with header block, one-sentence Big Idea, pre-class prep, 4-6 timed segments each with slide cues, mini-lecture bullets, named active-learning moves with prompts and timing, closing minute paper, outcome alignment, equity protocols, and slide deck skeleton.
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

Recommended Prompts

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.