El Auditor de Fiabilidad de Resultados de IA: Convierte Cualquier Informe Generado por IA en un Borrador Verificado y Contrastado
Por qué importa este prompt
In a well-documented 2023 case, two New York lawyers were sanctioned after submitting a legal brief containing six fake case citations fabricated by ChatGPT — neither lawyer had checked the citations before filing. Fabricated AI statistics in a board memo, a client proposal, or a published article carry the same risk on a smaller scale: a wrong number gets repeated by others and traced back to its source, a misattributed quote can trigger a correction request or a direct complaint from the person quoted, and a confidently stated falsehood is more dangerous than an admitted uncertainty, precisely because nobody feels the need to double-check something that sounds sure of itself.
Para qué lo usamos
A marketing manager used ChatGPT to draft a competitive analysis report due to the VP of Sales in 45 minutes. The report cites specific market share percentages, a quote from a named industry analyst, and three statistics about competitor pricing — none of which the manager has independently verified, and there's no time to research each one from scratch before the meeting.
Prompt
Role: You are a rigorous fact-checking editor whose job is to catch errors before they reach a client, executive, or publication — not to praise or rewrite the work. Context: I generated the following content using AI: [PASTE AI-GENERATED CONTENT HERE]. This will be used for: [DESCRIBE THE STAKES, e.g. "a client-facing report", "an internal board memo", "a public blog post"]. I do not have time to manually verify every claim, so I need you to systematically flag what needs checking before I send this. Task: Go through the content section by section and produce a structured audit that: 1. Lists every specific factual claim (statistics, dates, names, quotes, citations, technical specs) as a separate item 2. For each claim, classify it as: VERIFIABLE (a specific source could confirm or deny this), UNVERIFIABLE AS STATED (too vague to check, e.g. "many experts agree"), or SUSPICIOUS (internally inconsistent, suspiciously precise, or matches a known pattern of AI-fabricated detail) 3. For any claim classified SUSPICIOUS, explain specifically why — e.g. "this statistic has no attributed source and doesn't match [known figure] from general knowledge", or "this quote is attributed to a real person but cannot be verified" 4. Flag any internal contradictions between different sections of the content 5. Note any claims stated with unwarranted confidence (absolute language like "always", "never", "proven" around claims that are actually contested or uncertain) Constraints: - Do not simply rewrite or improve the prose — your only job is verification triage - Do not assume a claim is true just because it sounds plausible or specific — AI-generated fabrications are often highly specific and plausible-sounding - If you genuinely cannot assess a claim without external lookup, say so explicitly rather than guessing - Prioritize the claims that would be most damaging if wrong, given what's at risk: [DESCRIBE WHAT'S AT RISK, e.g. "client trust", "legal exposure", "public credibility"] Output Format: ## Verification Priority List [Ranked list of the 3-5 claims most critical to verify before sending, with why] ## Full Claim Audit [Table: Claim | Classification | Notes] ## Internal Contradictions [List, or "None found"] ## Overconfident Language [List of phrases with suggested softer alternatives] ## Bottom Line [One paragraph: safe to send as-is, safe with minor edits, or needs a fact-check pass before it goes anywhere]
Resultado
Verification Priority List
- 34% market share claim for Competitor X — This specific figure appears with no cited source and will likely be the first number the VP questions. If wrong, it undermines the entire report's credibility.
- Quote attributed to "Sarah Chen, Gartner analyst" — A named, verifiable person is quoted with a specific opinion. If this person didn't say this, or doesn't hold this role at Gartner, this is a serious misattribution risk.
- "Competitor pricing dropped 18% in Q3" — A precise, checkable pricing claim. Public pricing pages or press releases may confirm or refute this quickly.
Full Claim Audit
| Claim | Classification | Notes |
|---|---|---|
| "Competitor X holds 34% market share" | SUSPICIOUS | No source cited; figure is suspiciously precise for a private company with no public market-share disclosures. Cross-check against IDC or Gartner public reports before using. |
| Quote from "Sarah Chen, Gartner analyst" | SUSPICIOUS | Cannot confirm this person exists at Gartner or made this statement. Models frequently generate plausible-sounding attributed quotes that are fabricated. Verify via Gartner's published research or remove the attribution. |
| "Competitor pricing dropped 18% in Q3" | VERIFIABLE | Specific and checkable against the competitor's public pricing page or press releases. |
| "The market is rapidly consolidating" | UNVERIFIABLE AS STATED | Too vague to check as written; would need a specific timeframe and metric to become verifiable. |
| "Competitor Y has been the clear leader for years" | SUSPICIOUS (overconfident) | Absolute language for a market described elsewhere in the same report as "highly competitive" — internally inconsistent framing. |
Internal Contradictions
The report calls the market "highly competitive with no dominant player" in the intro paragraph, then later states Competitor Y has been "the clear leader for years." These two framings can't both be accurate — pick one and verify it before sending.
Overconfident Language
- "proven to be the top choice" → "reported by multiple sources to be a leading choice"
- "will definitely continue" → "is likely to continue, based on current trends"
Bottom Line
Not safe to send as-is. The market share figure and the Gartner analyst quote are both high-risk fabrication candidates that would be embarrassing if wrong in front of the VP of Sales — verify those two first, even if nothing else gets checked. The pricing claim is quick to confirm via public sources. Budget fifteen minutes for these three checks before sending.
La mayoría de las personas que le piden a una IA que "revise esto" reciben como respuesta un mensaje indicando que el contenido parece correcto — porque una petición genérica de verificar la exactitud no es una tarea real, sino una solicitud de tranquilidad, y la tranquilidad es precisamente lo que un modelo de lenguaje tiende a ofrecer cuando la instrucción no le obliga a hacer lo contrario.
Este prompt reemplaza esa petición vaga con un procedimiento de auditoría real: clasificar cada afirmación factual según su verificabilidad, explicar con precisión por qué las más arriesgadas lo son, y concluir con un veredicto concreto en lugar de un consuelo genérico.
Por qué clasificar afirmaciones en lugar de simplemente "revisarlas"
Pedirle a un modelo que "compruebe si hay errores" no le da ninguna tarea concreta — solo puede releer el texto y reportar una impresión vaga. Imponer una clasificación triple (verificable, no verificable tal como está formulada, sospechosa) convierte la verificación en una tarea de ordenación mecánica que el modelo puede ejecutar afirmación por afirmación, en lugar de un juicio abierto que probablemente sellará sin más. La categoría SOSPECHOSA apunta específicamente al fallo que más importa: los detalles fabricados por IA tienden a ser muy específicos y de apariencia plausible — un analista con nombre y apellido, un porcentaje preciso, una fecha concreta — lo que los hace peligrosos y exactamente lo que una revisión vaga del tipo "¿esto parece correcto?" pasará por alto.
Por qué la verificación entre modelos importa más aquí que en otros contextos
Un modelo al que se le pide que audite su propio output, o el output de un modelo con datos de entrenamiento y tendencias similares, tiene menos probabilidades de señalar una fabricación que encaje con sus propios patrones habituales de especificidad confiada. Ejecutar la auditoría con un modelo diferente — idealmente de un laboratorio distinto — significa que el auditor no comparte los mismos puntos ciegos que el generador. Este es el cambio con mayor apalancamiento disponible: el prompt funciona con cualquier modelo, pero funciona mejor entre modelos distintos que dentro de uno solo.
La restricción que más importa: no reescribir
La instrucción prohíbe explícitamente que el modelo mejore la prosa. Sin esa restricción, los modelos siguen su instinto más fuerte — mejorar el texto — lo que produce un borrador pulido en lugar de un informe de riesgos, y entierra silenciosamente la señal de verificación que realmente necesitas bajo cambios estilísticos que no pediste. Separar "¿es esto verdad?" de "¿está bien escrito?" mantiene la auditoría centrada en el único trabajo para el que existe.
Cómo adaptarlo
El campo de stakes en la sección de contexto cumple una función real: nombrar lo que está en juego (la confianza de un cliente, exposición legal, una decisión de consejo de administración) le indica al modelo cómo priorizar su lista de verificación, ya que una estadística incorrecta en un documento interno de brainstorming importa mucho menos que el mismo error en un comunicado de prensa público. Rellénalo de forma específica en lugar de dejarlo genérico — cuanto más nítido sea el riesgo, más precisa será la clasificación.