The advisor tool lets a faster, lower-cost executor model consult a higher-intelligence advisor model mid-generation for strategic guidance. The advisor reads the full conversation, produces a plan or course correction, and the executor continues with the task.

This pattern fits long-horizon agentic workloads (coding agents, computer use, multistep research pipelines) where most turns are mechanical but having an excellent plan is crucial. You get close to advisor-solo quality while the bulk of token generation happens at executor-model rates. For measured results, including how the benefit shrinks as the executor's own capability approaches the advisor's, see Optimizing for cost and intelligence.

sequenceDiagram
  participant U as Your application
  participant E as Executor model
  participant A as Advisor model

  U->>E: Request with advisor tool
  note over E: Executor begins the task
  E->>A: server_tool_use (server-side)
  note over A: Reads the full transcript,<br/>returns strategic guidance
  A-->>E: advisor_tool_result
  note over E: Executor continues,<br/>informed by the advice
  E-->>U: Response

To learn how zero data retention (ZDR) applies to this feature, see API and data retention.

本篇目录

• When to use it
• Quick start
• How it works
• Tool parameters
• Response structure
• Multi-turn conversations
• Streaming
• Usage and billing
• Advisor prompt caching
• Combining with other tools
• Best practices
• Model compatibility
• Advisor on Claude Managed Agents
• Next steps