O Explicador Improvável: Transforme um Tema Complexo em um Diálogo Entre Dois Personagens Que Nunca se Encontrariam
Porque é que este prompt importa
Technically accurate explanations that nobody remembers are functionally useless — teams end up answering the same question in every onboarding cohort, every customer call, every all-hands, because the written explanation never stuck. A memorable character-driven version gets repeated by employees in their own words to customers and colleagues, which is the actual goal of an internal explainer document; the alternative is a Slack channel where the same senior engineer re-explains hallucination from scratch every few weeks because the doc nobody reads isn't doing its job.
Para que o usamos
A developer relations writer at an AI company has been asked to add a plain-English explanation of why language models hallucinate to the new-hire onboarding doc, after the third all-hands where a non-technical new employee asked why the AI just made something up. The existing explanation is three paragraphs of next-token-prediction jargon that nobody reads past the first sentence, and leadership wants something people will actually remember when a customer asks them the same question.
Prompt
Role: Act as a skilled science communicator and dialogue writer who specializes in explaining complex topics through character-driven scenes rather than direct exposition. Context: I need to explain [COMPLEX TOPIC] to [TARGET AUDIENCE, e.g., "non-technical new hires" or "a general newsletter audience"]. Use two characters who would never normally meet or interact: [CHARACTER 1 — a profession, era, or personality type] and [CHARACTER 2 — a different profession, era, or personality type]. Character 1 has a plausible reason to be explaining the topic to Character 2 [OPTIONAL: describe the reason, or let the model invent one]. Task: Write a short dialogue (400-600 words) where Character 1 explains [COMPLEX TOPIC] to Character 2 entirely through analogies, comparisons, and vocabulary native to Character 2's world — not generic analogies, but ones specifically drawn from Character 2's actual profession, era, or experience. Constraints: No jargon dumps and no as-you-know exposition — Character 2 does not already understand the topic. Every analogy must be technically accurate when mapped back to the real concept; a vivid analogy that is factually wrong is worse than no analogy at all. Character 2 must ask at least one genuinely skeptical or confused question, the kind a real newcomer would ask, not a softball. End the dialogue with Character 2 restating the core concept correctly in their own words — this doubles as an accuracy check on the whole explanation. Output Format: Script format — character name as a label before each line, natural conversational dialogue, brief stage directions only in [brackets] where needed for context. No narration paragraphs outside the dialogue itself.
Resultado
[A carnival fortune-telling tent, 1920s. MADAME VESTRA, a fortune teller, sits across from JUNE, a software QA tester who has wandered in out of curiosity.]
JUNE: So people pay you for this? Just... predictions?
MADAME VESTRA: Predictions, yes. But here's my secret, dear — I never see the future. I complete sentences. Someone says "my mother always told me I'd never..." and I finish it with whatever sounds truest for their face, their clothes, the way they hold their hands. I'm very good at finishing sentences that sound right.
JUNE: That's... actually kind of how the AI models at my job work. They don't know facts, they predict the next likely word.
MADAME VESTRA: Exactly so! And here is where it goes wrong for both of us — sometimes I finish a sentence so confidently, so smoothly, that even I believe it for a moment. The client leaves certain I saw something true. I saw nothing. I only saw what sounded complete.
JUNE: Wait, but how is that different from just lying?
MADAME VESTRA: A liar knows the truth and hides it. I never had the truth to hide. I only ever had "what comes next, plausibly." That's worse in a way — you can catch a liar in a contradiction. You cannot catch someone who was never claiming to know, only claiming to sound right.
JUNE: So when my AI model states a fake statistic with total confidence...
MADAME VESTRA: It isn't lying to you, dear. It's finishing your sentence the way I finish my clients' fortunes — fluently, convincingly, and with no idea whether it's true. The danger was never the wrongness. It's that wrong and right sound exactly the same coming out.
JUNE: ...So the model doesn't know it's wrong. It just predicted the most likely-sounding next words, and sometimes likely-sounding and true aren't the same thing.
MADAME VESTRA: Now you understand my whole profession.
A maioria das explicações geradas por IA falha pelo mesmo motivo que os slides de PowerPoint falham: informação tecnicamente correta que ninguém lembra trinta segundos depois. O Explicador Improvável se baseia numa aposta simples — uma combinação de personagens genuinamente estranha obriga o modelo a encontrar analogias reais em vez de genéricas, porque uma vidente e uma testadora de QA não compartilham vocabulário, então cada comparação precisa ser conquistada.
Por que o descompasso é todo o mecanismo
Se você pedir a um modelo que explique alucinações usando um personagem de professor genérico, você recebe analogias genéricas e esquecíveis — do tipo que poderia se aplicar a quase qualquer tema apenas trocando os substantivos. Forçar uma combinação estranhamente específica (uma vidente dos anos 1920, uma testadora de QA moderna) torna impossíveis as analogias preguiçosas e intercambiáveis. O modelo precisa recorrer a detalhes que realmente sejam fiéis ao mundo daquele personagem específico, o que produz comparações mais afiadas e precisas como efeito colateral de manter o personagem.
Por que a pergunta cética importa
Um diálogo em que o segundo personagem apenas concorda com a cabeça não ensina nada — é exposição disfarçada. Exigir uma pergunta genuinamente confusa ou cética (espera, mas como isso é diferente de simplesmente mentir?) obriga a explicação a abordar o real ponto de confusão que um recém-chegado encontra, não o ponto que o explicador presume ser confuso.
Por que o final é uma verificação de precisão embutida
Fazer com que o segundo personagem reafirme corretamente o conceito no final cumpre dupla função: dá ao leitor um resumo limpo e citável para levar consigo, e obriga o modelo a verificar se sua própria explicação realmente se resolveu em algo verdadeiro — se o Personagem 2 não conseguir reafirmar corretamente o conceito, o diálogo não explicou nada, apenas encenou uma cena.
Onde isso se prova útil
Documentos de integração de novos funcionários, FAQs internas, posts de blog que explicam produtos técnicos a leitores não técnicos, materiais didáticos, e qualquer situação em que a mesma explicação precise sobreviver a ser recontada por outra pessoa com suas próprias palavras — que é o verdadeiro teste de se uma explicação funcionou.