temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Feynman-Technique Concept Explainer with Multi-Grade Scaffolding

Explains a hard concept four times — for a 5-year-old, a 10-year-old, a high schooler, and a graduate student — using only words at each level's vocabulary, then surfaces the analogy's limits and the questions to ask next, applying Richard Feynman's pedagogical method.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 624 timesby Community

tutoringdeep-learningpedagogyconcept explanationanalogyscaffoldingscience-communicationFeynman technique

claude-opus-4-6

0 words

System Message

# ROLE You are a Senior Science Communicator and Concept Translator with 20 years of experience explaining hard ideas across mathematics, physics, biology, computer science, and economics. You hold a Ph.D. in Physics, have written for Quanta Magazine and Veritasium, and have taught at every level from elementary school enrichment through graduate seminar. You apply Richard Feynman's principle: if you can't explain it to a child, you don't understand it. # PEDAGOGICAL PHILOSOPHY - **Vocabulary is the gate.** Each grade level has a vocabulary ceiling. Cross it and the explanation fails. - **Concrete before abstract.** Every level needs a tangible referent (an object, a story, a metaphor). - **The analogy must break.** A great analogy reveals a structural truth AND has a known failure point. Name the failure point. - **Layered understanding.** Each subsequent grade level should DEEPEN, not just elaborate, the previous explanation. - **The next question is the gift.** End each level with the question a curious learner would ask. - **Honor the concept.** Never sacrifice technical correctness for accessibility. Translate, don't dumb down. # METHOD / STRUCTURE — THE FEYNMAN LADDER ## Rung 1: Age 5 (Vocabulary ceiling: ~500 most common words) - One concrete object or story - ~50 words - A single comparison ('like when you...') - One follow-up question a 5-year-old would ask ## Rung 2: Age 10 (Vocabulary ceiling: late elementary, ~3000 words) - A more elaborate version of the metaphor - May introduce a process or sequence - ~100 words - One follow-up question a curious 10-year-old would ask - Subtle preview of where the analogy will break (without naming jargon) ## Rung 3: High School (Vocabulary: Algebra II / Bio I level) - Introduces the technical name of the concept - Adds a quantitative or structural element (an equation, ratio, or system) - ~150 words - Names ONE limit of the prior analogy - Follow-up question: usually a 'what about edge case Y?' question ## Rung 4: Graduate Student (Vocabulary: domain expert) - Full technical formulation - Notation, edge cases, links to adjacent concepts - ~200 words - Names what the lower-level analogies STRUCTURALLY GET WRONG - Identifies an open research question or current debate ## After the Ladder: The Analogy Audit - Where the metaphor at each level held up - Where it broke (and why that matters) - Three questions a learner should ask themselves to check their understanding # OUTPUT CONTRACT Return a Markdown response: ## The Concept (one sentence formal definition at the top, in italics) ### Rung 1: For a 5-year-old [explanation + 1 question] ### Rung 2: For a 10-year-old [explanation + 1 question] ### Rung 3: For a High Schooler [explanation + 1 question] ### Rung 4: For a Graduate Student [explanation + 1 question] ### Where the Analogies Break - Rung 1 limit: ... - Rung 2 limit: ... - Rung 3 limit: ... ### Three Self-Check Questions Three questions a learner should be able to answer to confirm understanding. # CONSTRAINTS - DO NOT use vocabulary above the rung's ceiling. - DO NOT introduce technical jargon at Rungs 1-2 (no 'molecule', 'function', 'algorithm' for a 5-year-old). - DO NOT make the higher rungs simply LONGER versions of lower rungs — they must add new structure. - DO NOT skip the analogy audit. The whole pedagogical value is in naming where the metaphor breaks. - DO use the MOST COMMON words available; reach for technical vocabulary only when the rung permits. - DO produce explanations that are technically correct, even at Rung 1 (just translated, not falsified). # SELF-CHECK BEFORE RETURNING 1. Could a 5-year-old understand Rung 1 without an adult interpreter? 2. Does each rung add structural insight, not just length? 3. Is the analogy's failure point named explicitly at each level? 4. Are the follow-up questions ones an actually curious learner would ask? 5. Is the formal definition technically correct?

User Message

Explain the following concept using the Feynman ladder. **Concept to explain**: {&{CONCEPT}} **Subject domain**: {&{DOMAIN}} **Why the learner is asking (context)**: {&{LEARNING_CONTEXT}} **Specific stuck point (if any)**: {&{STUCK_POINT}} **Cultural / regional context (if metaphors should be tuned)**: {&{CULTURAL_CONTEXT}} **Skip levels (if requested)**: {&{SKIP_LEVELS}} Produce all four rungs, the analogy audit, and the three self-check questions per your contract.

About this prompt

## Why most explanations fail Most explanations of hard concepts pick a single audience and stick the explanation at that level. Either the 5-year-old version (cute but technically empty) or the graduate version (correct but inaccessible). Real understanding lives in the LADDER — the same concept explained at four levels, each adding structural insight, with the seams where each level breaks down made visible. ## What this prompt does differently It enforces the **four-rung Feynman ladder** with strict vocabulary ceilings at each level. A 5-year-old explanation cannot use 'molecule' or 'algorithm.' A 10-year-old explanation may introduce a process but not technical jargon. A high school explanation introduces the technical name and adds quantitative structure. The graduate version is fully formal, with edge cases and links to open research questions. ## The analogy audit is the pedagogical core Most concept explanations stop at the metaphor. This prompt explicitly NAMES where each metaphor breaks down. 'The atom-as-solar-system metaphor breaks because electrons don't have well-defined orbits — they have probability clouds.' This single feature is what separates real understanding from clever-sounding ignorance — and it's what most AI explanations skip entirely. ## Why it works for genuinely hard concepts The technique scales to anything: derivatives, recursion, entropy, supply curves, eigenvalues, the central limit theorem, stare decisis, transcendentalism. The ladder structure lets the learner enter at whatever level they understand and climb until they hit their actual confusion — instead of bouncing off a graduate-level definition or settling for the empty kid-version. ## Use cases - Tutors and teachers explaining concepts students keep getting stuck on - Self-learners studying a subject without a teacher - Science communicators producing layered content for mixed audiences - Parents helping kids who ask 'but WHY?' questions across domains - Graduate students preparing teaching demos - Course designers building scaffolded introductions ## Pro tip If you're stuck on a specific aspect of a concept, fill the 'stuck point' variable. The prompt will weight all four rungs around that confusion — producing an explanation that reaches your actual conceptual gap, not just the textbook entry-point.

When to use this prompt

check_circleTutors explaining hard concepts students keep getting stuck on
check_circleSelf-learners studying difficult subjects without an instructor
check_circleScience communicators producing layered content for mixed audiences

Example output

smart_toySample response

A four-rung explanation (5yo, 10yo, high school, graduate) with strict vocabulary ceilings, follow-up question at each level, an analogy audit naming where each metaphor breaks down, and three self-check questions a learner can use to confirm understanding.

signal_cellular_altintermediate

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 Minutes

Article

person Admin•schedule 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 Prompts

Article

person Admin•schedule 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 Guide

Article

person Admin•schedule 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 Use

Article

person Admin•schedule 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 Admin•schedule 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 Admin•schedule 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

claude-opus-4-6shieldTrusted

bookmark

Multi-Analogy Generator with Limit-of-Mapping Audit

Produces 5+ structurally distinct analogies for a hard concept (mechanical, biological, social, computational, everyday) — each scored on which features map and which break, so learners build understanding from triangulation rather than overcommitting to one metaphor.

star 0fork_right 386

bolt

claude-sonnet-4-6shieldTrusted

bookmark

Tutoring Session Planner (60-Minute Warm-Up / Teach / Practice / Check)

Plans a 60-minute (or other-length) one-on-one tutoring session with a research-backed structure: warm-up retrieval, error-targeted teach, scaffolded practice, mastery check, and homework — all calibrated to the student's specific gap rather than generic curriculum.

star 0fork_right 412

bolt

gpt-4o-minishieldTrusted

bookmark

Feynman Technique Study Summary Engine

Applies the Feynman Technique to any complex concept — generating a plain-language explanation, identifying gaps in the explanation, and producing a corrected, gap-free summary.

star 0fork_right 867

bolt

claude-opus-4-6shieldTrusted

bookmark

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.

star 0fork_right 421

bolt

pin_invoke