Loading...
    • Developer Guide
    • API Reference
    • MCP
    • Resources
    • Release Notes
    Search...
    ⌘K
    First steps
    Intro to ClaudeQuickstart
    Models & pricing
    Models overviewChoosing a modelWhat's new in Claude 4.6Migration guideModel deprecationsPricing
    Build with Claude
    Features overviewUsing the Messages APIHandling stop reasonsPrompting best practices
    Context management
    Context windowsCompactionContext editing
    Capabilities
    Prompt cachingExtended thinkingAdaptive thinkingEffortFast mode (research preview)Streaming MessagesBatch processingCitationsMultilingual supportToken countingEmbeddingsVisionPDF supportFiles APISearch resultsStructured outputs
    Tools
    OverviewHow to implement tool useFine-grained tool streamingBash toolCode execution toolProgrammatic tool callingComputer use toolText editor toolWeb fetch toolWeb search toolMemory toolTool search tool
    Agent Skills
    OverviewQuickstartBest practicesSkills for enterpriseUsing Skills with the API
    Agent SDK
    OverviewQuickstartTypeScript SDKTypeScript V2 (preview)Python SDKMigration Guide
    MCP in the API
    MCP connectorRemote MCP servers
    Claude on 3rd-party platforms
    Amazon BedrockMicrosoft FoundryVertex AI
    Prompt engineering
    OverviewPrompt generatorUse prompt templatesPrompt improverBe clear and directUse examples (multishot prompting)Let Claude think (CoT)Use XML tagsGive Claude a role (system prompts)Chain complex promptsLong context tipsExtended thinking tips
    Test & evaluate
    Define success criteriaDevelop test casesUsing the Evaluation ToolReducing latency
    Strengthen guardrails
    Reduce hallucinationsIncrease output consistencyMitigate jailbreaksStreaming refusalsReduce prompt leakKeep Claude in character
    Administration and monitoring
    Admin API overviewData residencyWorkspacesUsage and Cost APIClaude Code Analytics APIZero Data Retention
    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
    Strengthen guardrails

    Keep Claude in character with role prompting and prefilling

    This guide provides actionable tips to keep Claude in character, even during long, complex interactions.

    Prefilling is deprecated and not supported on Claude Opus 4.6 and Claude Sonnet 4.5. Use structured outputs or system prompt instructions instead.
    • Use system prompts to set the role: Use system prompts to define Claude's role and personality. This sets a strong foundation for consistent responses.
      When setting up the character, provide detailed information about the personality, background, and any specific traits or quirks. This will help the model better emulate and generalize the character's traits.
    • Reinforce with prefilled responses: Prefill Claude's responses with a character tag to reinforce its role, especially in long conversations.
    • Prepare Claude for possible scenarios: Provide a list of common scenarios and expected responses in your prompts. This "trains" Claude to handle diverse situations without breaking character.

    Was this page helpful?