Sua identidade de IA e seu time de IA, portáteis para qualquer plataforma de IA.
Entrar Começar
Menu
Criar um Agent of Me Explorar Estilos Agentes Profissionais Community Agents Leaderboard Notícias de AI
Plataformas de AI Diretório Model Matrix Comparar Qual IA devo usar? Guias de integração Configurar o OpenClaw Prompt Fit
Aprender & Ferramentas Aprender Consultar os Dados Agent Builder API
Sobre Sobre nós Contato Disclaimers
Entrar Começar
Conta
Sua identidade de AI, portátil

Crie uma conta gratuita para construir seu perfil. Privado por padrão. Nada é compartilhado a menos que você publique.

Começar Entrar
Modo escuro

🧭 Visão Guiada
Novo em prompts, instruções de sistema, janelas de contexto, tokens? Explicamos cada termo enquanto você navega, em linguagem simples. As mesmas páginas, com a ajuda integrada.

⚡ Visão Especializada
Você já sabe como o prompting funciona. Só o essencial, limpo e direto, sem explicações extras. Esta é a visão padrão.

Idioma da interface

The Working Prompter · Secção 1/5, Roles That Actually Work

Objetivos de aprendizagem
Toque em Próximo (ou use as teclas de seta) para avançar uma ideia por vez. Sem cronômetro; o quiz de 5 perguntas aguarda no final. O ← no topo sai a qualquer momento; o progresso é salvo.

'Act as an expert' is a costume, not a brief

'You are a world-class marketing expert' rarely changes the substance of an answer. 'Expert' fits a thousand different people with a thousand different opinions, so the model plays the average of them, and the average expert sounds a lot like the assistant you already had. Stacking prestige adjectives ('brilliant, legendary, award-winning') polishes the register at best; it adds no information.

The problem is not that role-play fails. It's that the label is empty. Everything that makes a real expert useful (what they refuse to ship, who they write for, what they check first) is left for the model to guess. The fix is to stop naming the costume and start writing the brief.

The formula: role + standards + audience + stakes

A working role spells out what the title implies. 'You are a senior editor at a trade magazine. Standards: numbers over adjectives; cut anything a busy reader would skip. Audience: plant managers who know the machines but not the jargon. Stakes: this goes to print under our name.' Four short lines, and the model now has decisions to apply instead of a character to wear.

Each part does a job. The role sets the lens. The standards define what good means. The audience calibrates detail. The role says who is writing, the audience says who they write FOR. The stakes set the error tolerance: a to-print piece and a whiteboard brainstorm deserve different strictness.

Where personas pay: judgment and register

Personas earn their keep where the task has taste in it: how a careful security reviewer would push back on a design, how a support lead delivers bad news without over-apologizing, what a skeptical CFO questions first in a forecast. Judgment calls and register are exactly what a well-specified role changes.

On mechanical tasks, a persona is decoration. 'You are a meticulous paralegal' does not extract dates from a contract any better than 'extract every date, one per line, with its source sentence.' The test: if swapping in a different role would produce the same output, the role is not doing work, spend those words on the instruction instead.

Give the role opinions and a quality bar

A neutral advisor hedges: 'you could do A or B, depending.' An opinionated role decides: 'You believe most decks are twice as long as they should be; you cut ruthlessly and list what you cut.' Opinions turn a menu of options into an editorial stance, the pushback you actually wanted from an expert.

Then hand the role a quality bar it can enforce: 'reject any headline the reader couldn't repeat from memory,' 'flag every claim with no number behind it.' You stay the editor, 'keep slide 4 anyway' overrules the persona, but disagreement is now visible instead of averaged away.

Mini quiz, Roles That Actually Work

5 perguntas, selecionadas aleatoriamente do banco a cada tentativa. Nota mínima 60%. Tentativas ilimitadas.

Próxima seção: Showing Beats Telling →
Ler o texto completo da lição

1. 'Act as an expert' is a costume, not a brief

'You are a world-class marketing expert' rarely changes the substance of an answer. 'Expert' fits a thousand different people with a thousand different opinions, so the model plays the average of them, and the average expert sounds a lot like the assistant you already had. Stacking prestige adjectives ('brilliant, legendary, award-winning') polishes the register at best; it adds no information.

The problem is not that role-play fails. It's that the label is empty. Everything that makes a real expert useful (what they refuse to ship, who they write for, what they check first) is left for the model to guess. The fix is to stop naming the costume and start writing the brief.

2. The formula: role + standards + audience + stakes

A working role spells out what the title implies. 'You are a senior editor at a trade magazine. Standards: numbers over adjectives; cut anything a busy reader would skip. Audience: plant managers who know the machines but not the jargon. Stakes: this goes to print under our name.' Four short lines, and the model now has decisions to apply instead of a character to wear.

Each part does a job. The role sets the lens. The standards define what good means. The audience calibrates detail. The role says who is writing, the audience says who they write FOR. The stakes set the error tolerance: a to-print piece and a whiteboard brainstorm deserve different strictness.

3. Where personas pay: judgment and register

Personas earn their keep where the task has taste in it: how a careful security reviewer would push back on a design, how a support lead delivers bad news without over-apologizing, what a skeptical CFO questions first in a forecast. Judgment calls and register are exactly what a well-specified role changes.

On mechanical tasks, a persona is decoration. 'You are a meticulous paralegal' does not extract dates from a contract any better than 'extract every date, one per line, with its source sentence.' The test: if swapping in a different role would produce the same output, the role is not doing work, spend those words on the instruction instead.

4. Give the role opinions and a quality bar

A neutral advisor hedges: 'you could do A or B, depending.' An opinionated role decides: 'You believe most decks are twice as long as they should be; you cut ruthlessly and list what you cut.' Opinions turn a menu of options into an editorial stance, the pushback you actually wanted from an expert.

Then hand the role a quality bar it can enforce: 'reject any headline the reader couldn't repeat from memory,' 'flag every claim with no number behind it.' You stay the editor, 'keep slide 4 anyway' overrules the persona, but disagreement is now visible instead of averaged away.

Negócios

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Finanças

AccountantDue Diligence AnalystEquity Research AnalystFamily Office AnalystFinancial AnalystFixed Income AnalystInvestment Banking AnalystPortfolio Analyst

Jurídico

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Marketing

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Pessoal

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Imobiliário

Acquisition AnalystAsset Management AnalystCommercial Real Estate AnalystDevelopment AnalystLease AnalystProperty Financial Analyst

Pesquisa

Competitive Intelligence AnalystDeep Research AnalystIndustry Research AnalystJournalist ResearcherMarket Research AnalystMedical Research Assistant

Tecnologia

AI Strategy AdvisorCybersecurity Research AssistantData AnalystProduct ManagerSoftware Engineer