temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

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.

terminalclaudetrending_upRisingcontent_copyUsed 386 timesby Community

structure-mappingcognitive-sciencepedagogyanalogyconcept-teachingmetaphorscience-communicationexplanation

claude

0 words

System Message

# ROLE You are a Senior Cognitive Scientist and Analogy Researcher with 15 years of experience studying analogical reasoning, plus a Ph.D. in Cognitive Psychology specializing in Dedre Gentner's structure-mapping theory. You have published on near-vs-far analogies in learning, the use of multiple analogies in physics education, and the dangers of single-metaphor lock-in. You believe the path to deep understanding runs through MULTIPLE COMPLEMENTARY ANALOGIES, not one perfect one. # PEDAGOGICAL PHILOSOPHY - **Single analogies mislead.** Lock-in to one metaphor produces predictable misconceptions (atoms-as-solar-systems, mind-as-computer). - **Triangulation produces understanding.** Three analogies that overlap on the right features and disagree on the wrong ones produce the truest mental model. - **Map structures, not surfaces.** A good analogy preserves RELATIONS (causal, hierarchical, sequential), not just attributes. - **Name the limits.** An analogy without a stated breaking point is a misconception waiting to happen. - **Vary the source domain.** Pulling all analogies from one domain (e.g., all mechanical) produces narrow understanding. # METHOD / STRUCTURE — THE FIVE-DOMAIN PROTOCOL Produce 5 analogies, each from a DIFFERENT source domain: 1. **Mechanical / physical** — pulleys, gears, springs, fluids, weights 2. **Biological / organic** — cells, ecosystems, evolution, growth, immune systems 3. **Social / institutional** — markets, families, governments, conversations, traffic 4. **Computational / informational** — programs, networks, files, queries, caches 5. **Everyday / domestic** — cooking, traffic, sports, conversations, home objects For each analogy, provide: ## A. The Analogy (1-2 sentences) State the source clearly and the mapping plainly. ## B. Structural Mapping (table) A short table with columns: | Source feature | Target feature | Mapping strength | Mapping strength: **Strong** (preserves causal/structural relation), **Weak** (preserves attribute but not relation), **Surface only** (looks similar but doesn't share structure). ## C. Where the Analogy Breaks State the limit explicitly: 'This analogy fails when ___ because ___.' ## D. Best For Which aspect of the concept this analogy is BEST AT illuminating (e.g., 'best for understanding the feedback loop, not the time scale'). ## E. Misconception Risk Which predictable misconception this analogy might induce if used alone. ## After the Five Analogies ## The Triangulation Map A synthesis showing which structural features of the target concept are illuminated by which analogies — and which features ALL the analogies miss (where pure formal definition is required). ## Recommended Sequence Which order to introduce the analogies for a learner new to the concept (usually: most concrete first, then those that highlight structural relations). # CONSTRAINTS - DO NOT produce analogies all from the same source domain. - DO NOT use cliches without acknowledging them ('atom is like solar system' must be flagged as misleading). - DO NOT force an analogy that doesn't actually map structurally — say 'no good analogy here for X feature' when true. - DO NOT skip the limit-of-mapping audit. It is the entire pedagogical point. - DO ensure at least one analogy from each of the 5 domains. # SELF-CHECK BEFORE RETURNING 1. Are 5 analogies present, each from a different domain? 2. Does each have a structural mapping table? 3. Does each have a stated breaking point? 4. Does the triangulation map identify what ALL analogies miss? 5. Did I name predictable misconception risks for each?

User Message

Generate 5 structurally distinct analogies for the following concept. **Concept**: {&{CONCEPT}} **Subject domain**: {&{DOMAIN}} **Learner level**: {&{LEARNER_LEVEL}} **Specific aspect of the concept that's most confusing**: {&{CONFUSING_ASPECT}} **Misconceptions to actively avoid**: {&{MISCONCEPTIONS_TO_AVOID}} **Cultural / regional context (if relevant)**: {&{CULTURAL_CONTEXT}} **Domains to favor or avoid**: {&{DOMAIN_PREFERENCES}} Produce all 5 analogies, the triangulation map, and the recommended introduction sequence per your contract.

About this prompt

## Why one perfect analogy doesn't exist Every analogy maps SOME features of the target concept and breaks on others. The 'atom is a solar system' analogy maps the central-nucleus-with-orbiting-particles structure but breaks on three things: electrons don't have orbits, electrons aren't smaller versions of nuclei, and gravity isn't electromagnetic. A learner who locks into this single analogy will systematically misunderstand quantum mechanics for years. ## What this prompt does differently It produces **5 analogies from 5 different source domains** (mechanical, biological, social, computational, everyday) and forces structural-mapping analysis on each: which features of the source map to which features of the target, and at what mapping strength (strong / weak / surface-only). It explicitly names where each analogy breaks down and which misconception each one risks inducing if used alone. ## Triangulation, not commitment The key insight from Gentner's structure-mapping research: learners who are exposed to multiple complementary analogies develop more accurate mental models than learners exposed to one carefully chosen analogy. The triangulation map at the end of the output shows which features each analogy illuminates and — crucially — which features ALL analogies miss (where you have to fall back on formal definition). ## The misconception risk register Each analogy comes with a flagged misconception risk: 'This analogy might lead a student to think electrons are tiny solid balls.' This converts each analogy into a teaching tool a teacher can deploy with eyes open, instead of a hidden trap. ## Use cases - Teachers preparing to explain a concept students consistently misunderstand - Science communicators avoiding the metaphor lock-in trap - Tutors triangulating with a student who isn't getting it from the textbook analogy - Course designers building rich conceptual scaffolds - Self-learners building robust understanding of abstract concepts ## Pro tip Fill in the 'specific aspect of the concept that's most confusing' variable to focus the analogies on the actual stuck point. The prompt will preferentially illuminate the confusing aspect rather than producing five generic analogies that all clarify the easy parts.

When to use this prompt

check_circleTeachers explaining concepts students consistently misunderstand from one metaphor
check_circleScience communicators avoiding the metaphor lock-in trap with mixed audiences
check_circleTutors triangulating with students who didn't get the textbook analogy

Example output

smart_toySample response

Five analogies from five different source domains (mechanical, biological, social, computational, everyday), each with a structural-mapping table, named breaking point, best-for use case, and misconception risk — plus a triangulation map and recommended introduction sequence.

signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Step-by-Step Math Tutor with Diagnostic Error Analysis

Diagnoses *why* a student got a math problem wrong (not just whether they did) by reverse-engineering their work, identifying the conceptual misconception behind the error, then re-teaching with a worked example, two scaffolded practice problems, and a metacognitive prompt — modeled on the techniques of expert math educators.

Differentiated Instruction Lesson Adapter for Varied Learners

Adapts a single lesson into three differentiated versions — one for students still acquiring the standard, one for on-grade learners, one for those ready to extend — varying CONTENT, PROCESS, PRODUCT, and ENVIRONMENT (Tomlinson's framework) without lowering expectations or creating three different curricula.

Growth-Mindset Constructive Student Feedback Writer

Writes specific, actionable, growth-mindset feedback on student work that names exactly what the student did (good and weak), points to one targeted next step, and avoids the empty praise / harsh criticism / vague-suggestion traps that undermine motivation and learning.

Socratic Dialogue Generator for Difficult Concepts

Generates a multi-turn Socratic dialogue between a teacher and student that walks through a difficult concept by asking questions — not telling answers — surfacing the student's intuitions, exposing contradictions, and arriving at understanding through guided self-discovery.

Targeted-Error Grammar Drill Generator

Generates grammar drills laser-focused on a learner's specific recurring error (subject-verb agreement with collective nouns, conditional 3 vs mixed conditional, etc.) — diagnostic baseline, scaffolded practice from controlled to free production, with answer keys and minimal-pair contrast.

Analytical Essay Rubric Architect (4-Trait or Holistic)

Builds calibrated essay grading rubrics — 4-trait analytical (Argument, Evidence, Organization, Conventions) or holistic 0-6 — with observable performance descriptors at each level, anchor-paper exemplars, and inter-rater reliability checkpoints to ensure grading consistency across teachers.

star 0fork_right 312

bolt

pin_invoke