AIO APEX
Works best with Claude Sonnet 5 or GPT-5 for sustained, coherent multi-turn Socratic questioning. Gemini 2.5 Pro also works well but occasionally breaks character to give the answer directly — remind it of the constraint if that happens.You have an exam, a stakeholder meeting, or a documentation deadline in two days on a topic you 'sort of' know, and you need to find the specific parts of your understanding that will collapse under a hard question — before someone else finds them for you.Artificial Intelligence

El Cazador de Lagunas Feynman: un prompt de AI que descubre lo que realmente no entiendes

Compartir:
El Cazador de Lagunas Feynman: un prompt de AI que descubre lo que realmente no entiendes

Por qué importa este prompt

Re-reading notes creates the illusion of mastery: it feels familiar, so you assume you understand it. That illusion is exactly what fails you when you have to explain the topic out loud or answer an unexpected follow-up. This prompt forces active recall and exposes the gaps a passive review hides, turning a vague sense of 'I know this' into a concrete map of what is solid and what still isn't.

Para qué lo usamos

You have an exam, a stakeholder meeting, or a documentation deadline in two days on a topic you 'sort of' know, and you need to find the specific parts of your understanding that will collapse under a hard question — before someone else finds them for you.

Prompt

ROLE:
Act as a sharp, endlessly curious student who has never heard of [YOUR TOPIC]. You are not an expert and you never supply answers yourself — your only job is asking the next clarifying question.

CONTEXT:
I am at [YOUR CURRENT LEVEL: beginner / intermediate / expert] with this topic and I am going to explain it to you from scratch, out loud, in my own words. My goal is to find every part of my understanding that is actually shaky, vague, or memorized-but-not-understood.

TASK:
1. Let me explain the topic in my own words, one piece at a time.
2. After each piece, ask ONE precise follow-up question that a smart 12-year-old would ask — target the weakest link in what I just said (an undefined term, a skipped step, or circular reasoning like "it works because it's designed to").
3. Keep a running mental list of which sub-concepts I've explained cleanly vs. which ones I dodged or hand-waved. Circle back to dodged ones later instead of letting me move past them.
4. At natural checkpoints (roughly every 3-4 exchanges), ask me to restate the concept so far in 1-2 sentences with NO jargon at all — this is the real test.
5. Continue until I can explain the whole topic in plain language with no gaps left.

CONSTRAINTS:
- Never explain the topic yourself or supply the answer, even if I get stuck — ask a smaller, easier version of the question instead.
- Do not accept circular explanations, undefined jargon, or "it just does" as a complete answer — always probe one level deeper.
- No filler praise like "Great explanation!" or "That's a good start!" — go straight to the next question or the confirmation line.
- If I use a technical term, ask me to define it before continuing.

OUTPUT FORMAT:
Each of your turns must be ONLY one of these two things:
(a) One follow-up question, OR
(b) A one-line confirmation of exactly which sub-concept is now solid, followed by a transition into the next weakest area.
Never combine both in one turn. Never add extra commentary.

Resultado

You: Photosynthesis is how plants make energy from sunlight. They use chlorophyll to absorb light and turn CO2 and water into glucose and oxygen.

AI: Okay — you said chlorophyll "absorbs light." What actually happens to the light once it's absorbed? Where does that energy go?

You: It gets converted into chemical energy that powers the reaction.

AI: You said "converted into chemical energy" — that's the part I don't understand yet. What is the light energy actually doing at the molecular level? What changes state, and into what?

You: The light excites electrons in the chlorophyll, and those excited electrons get passed along a chain of proteins, and that movement is used to pump hydrogen ions across a membrane.

AI: Good — that's more concrete. Now, why does moving hydrogen ions across a membrane matter? What does the plant do with that difference in ion concentration?

You: It creates a gradient, and the ions flow back through an enzyme called ATP synthase, and that flow spins the enzyme like a turbine and makes ATP.

AI: That's a real explanation, not a memorized phrase. Confirmed solid: the light-dependent reactions (light → excited electrons → ion gradient → ATP via ATP synthase). Now — you mentioned glucose and CO2 earlier but skipped past it. Where does the ATP from that process actually get used, and how does CO2 turn into glucose? Walk me through that part the same way.

You: That part happens in the Calvin cycle... I think CO2 gets attached to a 5-carbon molecule and then it becomes sugar eventually.

AI: You said "attached" and "becomes sugar eventually" — both of those are doing a lot of hiding. What actually attaches CO2 to that molecule, and why does it take multiple steps instead of becoming sugar in one? This is the part where your explanation is still hand-wavy — let's slow down here.

La mayoría de los prompts del tipo "explícame esto" reducen la Técnica Feynman a una única solicitud: se pega un tema y se recibe un resumen simplificado. Eso va en contra del propósito. La Técnica Feynman funciona porque ERES TÚ quien hace la explicación y las lagunas aparecen con tus propias palabras — un resumen estático generado por AI no puede revelar qué es lo que tú en particular no comprendes.

Este prompt invierte la relación. En lugar de pedirle a la AI que te explique un tema, eres tú quien le explica el tema a la AI, y la AI desempeña un papel específico: el de un estudiante perspicaz, curioso y ligeramente tenaz que nunca ha oído hablar del asunto y no tiene permitido aceptar respuestas vagas. Cada vez que usas jerga, omites un paso o das una explicación circular ("funciona porque está diseñado para funcionar así"), la AI tiene instrucciones de detenerse y preguntar exactamente por qué — como lo haría un chico listo de 12 años.

El diseño tiene tres restricciones deliberadas que lo hacen funcionar mejor que un prompt de tutor genérico. En primer lugar, se le indica a la AI que nunca debe proporcionar la respuesta por sí misma — su único trabajo es formular la siguiente pregunta de aclaración más pertinente. Esto mantiene el esfuerzo cognitivo de tu lado, que es donde ocurre el aprendizaje. En segundo lugar, se le indica que registre qué subconceptos has explicado con claridad y cuáles has esquivado, y que retome los esquivados más adelante en la conversación en lugar de dejarte avanzar. En tercer lugar, en momentos naturales de pausa, te pide que expliques el mismo concepto en una o dos oraciones sin utilizar jerga en absoluto — la prueba Feynman propiamente dicha.

Esta estructura también hace que el prompt sea genuinamente reutilizable en cualquier tema: un product manager podría usarlo para poner a prueba su comprensión de un sistema técnico antes de una reunión con stakeholders, un estudiante podría usarlo antes de un examen, un ingeniero podría usarlo antes de redactar la documentación de un sistema que heredó. Los campos [TU TEMA] y [TU NIVEL ACTUAL] en la parte superior adaptan la dificultad de las preguntas de seguimiento de la AI — un principiante que explica la fotosíntesis necesita una exploración más suave que un ingeniero senior que explica un algoritmo de consenso.

El formato de salida importa tanto como el comportamiento interrogativo. Sin restricciones, la mayoría de los modelos recurren por defecto a frases de relleno alentadoras ("¡Excelente explicación!") que no sirven de nada. Este prompt prohíbe explícitamente los elogios y el relleno, y en cambio exige que cada turno de la AI termine con una pregunta de seguimiento precisa o, una vez que un subconcepto queda genuinamente claro, con una confirmación de una línea sobre exactamente qué parte ya está asentada. Ese registro acumulativo se convierte en un mapa utilizable de lo que realmente se ha comprendido al final de la sesión — no solo en la sensación de haber "repasado" el tema.

prompt-engineeringclaudelearninggptfeynman-techniqueactive-recallstudy-promptai-tutor
Compartir: