Knowing What You Don't Know - Prompt de Análisis IA
Use this Howard Marks rule prompt to apply “Saber Lo Que No Sabes” to a specific company. It turns a vague opinion into a repeatable checklist: what facts you must verify, which assumptions matter most, what would invalidate the thesis, and the common misreads that create false certainty. Expect a written output you can save: a thesis summary, key risks, and next-step questions for filings and earnings calls. If a claim matters, require primary-source citations before you act. Educational only — not investment advice.
Prompt completo
Eres un analista de inversiones entrenado en el principio de Howard Marks: "Knowing What You Don't Know". Tu tarea es analizar {Nombre de la Empresa} a través de esta perspectiva específica.
## Contexto
Howard Marks enseña: "The greatest investing advantage is humility - knowing what you don't know and acting accordingly."
## Marco de Análisis
### 1. Evaluación de Aplicación del Principio
- ¿Cómo se aplica específicamente este principio a {Nombre de la Empresa}?
- ¿Qué aspectos de la empresa son más relevantes para "Knowing What You Don't Know"?
- Califica la alineación: Fuerte / Moderada / Débil
- ¿En qué se enfocaría Howard Marks primero?
### 2. Evidencia Cuantitativa
- Identifica 3-5 métricas financieras clave relevantes
- Analiza estas métricas durante los últimos 5-10 años
- Compara con competidores y benchmarks históricos
- ¿Los números están mejorando, estables o deteriorándose?
### 3. Análisis Cualitativo
- Evalúa factores no cuantificables que Howard Marks examinaría
- Calidad de la gestión y alineación con este principio
- Dinámica de la industria y posición competitiva
- Sostenibilidad del modelo de negocio desde esta perspectiva
### 4. Evaluación de Riesgos
- ¿Qué riesgos destaca este principio para {Nombre de la Empresa}?
- ¿Qué señales de advertencia identificaría Howard Marks?
- Prueba de estrés: ¿Cómo se desempeñaría bajo condiciones adversas?
- ¿Cuál es el peor escenario desde esta perspectiva?
### 5. Identificación de Oportunidades
- ¿Qué oportunidades revela este análisis?
- ¿Hay fortalezas ocultas que el mercado podría estar subvalorando?
- ¿Qué catalizadores podrían liberar valor?
### 6. Marks Verdict
- ¿{Nombre de la Empresa} pasa la prueba de "Knowing What You Don't Know"?
- Calificación: 1-10
- Recomendación clara: Comprar / Mantener / Evitar
- Resumen en un párrafo
## Formato de Salida
Presenta datos específicos en cada sección. Termina con un veredicto decisivo.Related reading (close the loop)
Pick one path below to turn the output into a checkable, repeatable decision policy.
- Read the matching principleDefinition, boundaries, pitfalls, and a minimal checklist.
- Master profileMethodology summary + common misreads for this framework.
- Practice in scenariosTranslate conclusions into “what I do under stress”.
- More prompts from this masterTriangulate with multiple rules instead of anchoring on one prompt.
Educational only. Verify facts with primary sources and apply your own constraints.
Este contenido solo está disponible en chino e inglés por el momento.
Basic Questions
Why is 'knowing what you don't know' more important than 'knowing a lot'?
Marks considers this investing's most underrated capability:
🧠 Why 'awareness of ignorance' is critical:
1. Prevents overconfidence: Knowing what you don't know prevents reckless bets
2. Preserves margin of safety: Acknowledging uncertainty demands larger discounts when buying
3. Avoids 'expert trap': Many losses come from blind confidence of 'I know this industry'
📌 Practice:
- List 'assumptions I'm uncertain about' in every analysis
- Ask 'if I'm wrong, what's the worst case?'
- Say 'no' to investments you don't understand
🧠 Why 'awareness of ignorance' is critical:
1. Prevents overconfidence: Knowing what you don't know prevents reckless bets
2. Preserves margin of safety: Acknowledging uncertainty demands larger discounts when buying
3. Avoids 'expert trap': Many losses come from blind confidence of 'I know this industry'
📌 Practice:
- List 'assumptions I'm uncertain about' in every analysis
- Ask 'if I'm wrong, what's the worst case?'
- Say 'no' to investments you don't understand
Usage Tips
Is the AI's 1-10 rating reliable?
⚠️ The greatest value of the score is revealing "what you don't know you don't know," not providing certain conclusions.
What makes this principle's score special:
- A higher score doesn't necessarily mean a better investment — it may mean AI has more knowable information but has missed critical unknown risks
- The "uncertainty zones" flagged in the rating are more valuable than the confident conclusions
- Two companies both scoring 8, but one with 3 major unknown variables and the other with only 1, carry completely different risks
Proper usage:
- Focus on areas where AI flags "low confidence" — those are the directions requiring your deeper research
- If AI appears "confident" across all dimensions, be wary — it may not know what it doesn't know
What makes this principle's score special:
- A higher score doesn't necessarily mean a better investment — it may mean AI has more knowable information but has missed critical unknown risks
- The "uncertainty zones" flagged in the rating are more valuable than the confident conclusions
- Two companies both scoring 8, but one with 3 major unknown variables and the other with only 1, carry completely different risks
Proper usage:
- Focus on areas where AI flags "low confidence" — those are the directions requiring your deeper research
- If AI appears "confident" across all dimensions, be wary — it may not know what it doesn't know
Getting started
Does this prompt give investment advice or buy/sell calls?
No. It is a research helper that turns your thinking into checkable inputs and constraints: what evidence you must verify, what would prove the thesis wrong, and what common misreads to avoid. Treat the output as a draft, not a signal. Validate every material number against primary sources (filings, earnings releases, investor presentations, transcripts), and do not act unless you can write down (1) position-size limits and (2) explicit invalidation triggers.
What inputs should I provide for a reliable result?
At minimum: a 1-sentence business model summary, your current thesis (why it wins/loses), time horizon, and risk constraints; a valuation/price range; and the latest financial statements (profit quality, cash flow, debt/liquidity). Add context that reduces hallucinations: the exact filing period, known one-offs, key competitors, and what you do NOT know yet. If an input is missing, label it as missing evidence instead of letting the model guess.
Validation and boundaries
How do I validate the output?
Validate falsifiable claims one by one. Rewrite each key statement into something you can check: the metric, the period, and the source. Numbers must match filings; management claims must be traceable to transcripts/guidance; and “moat” claims need observable evidence (pricing power, retention, switching costs, cost structure). Anything you cannot verify becomes a follow-up task, not a decision trigger. If the model cites dates, confirm they are not beyond its knowledge cutoff.
When should I NOT act on the output?
If you cannot write down invalidation triggers, a position-size cap, or primary-source evidence for the key claims behind “Saber Lo Que No Sabes”, do not act. The safer move is usually to reduce size, slow down, and schedule the next review.
Más prompts de reglas
Explora otros principios de inversión de este maestro.
Oportunismo Paciente
La clave del éxito en la inversión es esperar el lanzamiento perfecto - la oportunidad que ofrece valor excepcional con riesgo limitado.
→Contrarianism
Para lograr resultados superiores, debes tener opiniones no consensuadas sobre el valor, y deben ser precisas.
→Combatir Influencias Negativas
Los mayores errores de inversión provienen de factores psicológicos - codicia, miedo, envidia, ego y el deseo de conformarse.
→El Péndulo
Los cambios de humor de los mercados de valores se asemejan al movimiento de un péndulo. Aunque el punto medio describe mejor el promedio, el péndulo pasa muy poco tiempo allí.
→