Official Technical Resources: Anthropic (page 1)
Official Technical Resources · Anthropic. Documentation, model cards, research and safety resources. This source has 269 entries admitted under this category's review policy, listed across 18 pages; each links directly to the original.
Authority tiers in this category: A1–A2.
Overview
Agent Skills
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
Overview
MCP tunnels
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
Overview
Tool use with Claude
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
Architecture and components
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
Authentication
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: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Bash tool
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: Code Execution and Sandboxing · AI Coding Tools
Link last checked: 2026-09-24
Batch processing
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
Browser use tool
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: Computer Use · AI Agent
Link last checked: 2026-09-24
Cache diagnostics
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: Prompt Caching · LLM Inference Optimization
Link last checked: 2026-09-24
Citations
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: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG)
Link last checked: 2026-09-24
Amazon Bedrock (Opus 4.6 and earlier)
Claude on Amazon Bedrock (Opus 4.6 and earlier)
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
Code execution 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: Code Execution and Sandboxing · AI Coding Tools
Link last checked: 2026-09-24
Keep thinking blocks valid
Compaction and preserved 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
Compaction
Compaction overview
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
Computer use 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: Computer Use · AI Agent
Link last checked: 2026-09-24