Official Technical Resources: Anthropic (page 2)
Official Technical Resources · Anthropic: 269 entries in total; this page lists entries 16–30.
Context editing
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: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Context windows
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: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Define 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
Effort
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: Reasoning Models · Model Selection and Cost
Link last checked: 2026-09-24
Extended thinking (legacy)
Extended 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
Files API
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
Fine-grained tool streaming
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: AI Agent · Tool Calling
Link last checked: 2026-09-24
Streaming refusals
Handle streaming refusals
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
How tool use works
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
Manage tool context
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: Context Compaction · Agent Memory
Link last checked: 2026-09-24
MCP connector
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
Security
MCP tunnels security
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
Memory tool
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: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Mid-conversation system messages and tool changes
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
Parallel 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