Official Technical Resources: Anthropic (page 3)
Official Technical Resources · Anthropic: 269 entries in total; this page lists entries 31–45.
PDF support
Adds official details that affect correct implementation, troubleshooting, security or selection; has independent evidentiary value.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Multimodal Models
Link last checked: 2026-09-24
Preserved thinking
Adds official details that affect correct implementation, troubleshooting, security or selection; has independent evidentiary value.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Reasoning Models · Model Selection and Cost
Link last checked: 2026-09-24
Programmatic tool calling
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Tool Calling
Link last checked: 2026-09-24
Prompt caching
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Prompt Engineering · Structured Outputs
Link last checked: 2026-09-24
Refusals and fallback
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · AI Red Teaming
Link last checked: 2026-09-24
Remote MCP servers
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Tool Calling
Link last checked: 2026-09-24
Search results
Adds official details that affect correct implementation, troubleshooting, security or selection; has independent evidentiary value.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG)
Link last checked: 2026-09-24
Server tools
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Tool Calling
Link last checked: 2026-09-24
Best practices
Skill authoring best practices
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Steering and cost control
Steering thinking
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Reasoning Models · Model Selection and Cost
Link last checked: 2026-09-24
Stop reasons and fallback
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Deployment Options
Link last checked: 2026-09-24
Streaming Messages
Streaming messages
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Deployment Options
Link last checked: 2026-09-24
Strict tool use
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Tool Calling
Link last checked: 2026-09-24
Structured outputs
Directly explains core mechanisms, capability limits or engineering decisions and continues to support understanding and practice.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Prompt Engineering · Structured Outputs
Link last checked: 2026-09-24
Task budgets (beta)
Task budgets
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Deployment Options
Link last checked: 2026-09-24