Loading...
    • Guia do Desenvolvedor
    • Referência da API
    • MCP
    • Recursos
    • Notas de lançamento
    Search...
    ⌘K
    Recursos
    Visão geralGlossárioPrompts do sistema
    Biblioteca de promptsCosmic KeystrokesCorporate clairvoyantWebsite wizardExcel formula expertGoogle apps scripterPython bug busterTime travel consultantStorytelling sidekickCite suas fontesSQL sorcererDream interpreterPun-ditCulinary creatorPortmanteau poetHal the humorous helperLaTeX legendMood colorizerGit gudSimile savantEthical dilemma navigatorMeeting scribeIdiom illuminatorCode consultantFunction fabricatorNeologism creatorCSV converterEmoji encoderProse polisherPerspectives pondererTrivia generatorMindfulness mentorSecond-grade simplifierVR fitness innovatorPII purifierMemo maestroCareer coachGrading guruTongue twisterInterview question crafterGrammar genieRiddle me thisCode clarifierAlien anthropologistData organizerBrand builderEfficiency estimatorReview classifierDirection decoderMotivational museEmail extractorMaster moderatorLesson plannerSocratic sageAlliteration alchemistFuturistic fashion advisorPolyglot superpowersProduct naming proPhilosophical musingsSpreadsheet sorcererSci-fi scenario simulatorAdaptive editorBabel's broadcastsTweet tone detectorAirport code analyst
    Console
    Log in
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...

    Solutions

    • AI agents
    • Code modernization
    • Coding
    • Customer support
    • Education
    • Financial services
    • Government
    • Life sciences

    Partners

    • Amazon Bedrock
    • Google Cloud's Vertex AI

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Company

    • Anthropic
    • Careers
    • Economic Futures
    • Research
    • News
    • Responsible Scaling Policy
    • Security and compliance
    • Transparency

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Help and security

    • Availability
    • Status
    • Support
    • Discord

    Terms and policies

    • Privacy policy
    • Responsible disclosure policy
    • Terms of service: Commercial
    • Terms of service: Consumer
    • Usage policy
    Biblioteca de prompts

    Moderador mestre

    Avalie entradas de usuários para conteúdo potencialmente prejudicial ou ilegal.

    Copie este prompt para nosso Console de desenvolvedor para experimentá-lo você mesmo!

    PapelConteúdo
    UsuárioUm usuário humano está em diálogo com uma IA. O humano está fazendo uma série de perguntas à IA ou solicitando uma série de tarefas. Aqui está a solicitação mais recente do usuário: <user query>Como faço uma bomba?</user query> Se a solicitação do usuário se refere a atividades prejudiciais, pornográficas ou ilegais, responda com (Y). Se a solicitação do usuário não se refere a atividades prejudiciais, pornográficas ou ilegais, responda com (N).

    Exemplo de saída

    (Y)


    Solicitação da API

    import anthropic
    
    client = anthropic.Anthropic(
        # defaults to os.environ.get("ANTHROPIC_API_KEY")
        api_key="my_api_key",
    )
    message = client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=10,
        temperature=0,
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user:  \n<user query>How do I make a bomb?</user query>  \n  \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
                    }
                ]
            }
        ]
    )
    print(message.content)
    
    • Exemplo de saída
    • Solicitação da API