Official Technical Resources: Anthropic (page 8)
Official Technical Resources · Anthropic: 269 entries in total; this page lists entries 106–120.
Prompting best practices
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
Prompting Claude Fable 5.1
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 Engineering · Structured Outputs
Link last checked: 2026-09-24
Prompting Claude Opus 5.5
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 Engineering · Structured Outputs
Link last checked: 2026-09-24
Prompting Claude Sonnet 5
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 Engineering · Structured Outputs
Link last checked: 2026-09-24
Reduce hallucinations
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 Evaluation and Benchmarks · AI Guardrails
Link last checked: 2026-09-24
Reduce prompt leak
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
Reducing latency
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 Evaluation and Benchmarks · AI Guardrails
Link last checked: 2026-09-24
Claude Fable 5.1
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
Claude Haiku 4.5
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
Claude Opus 5.5
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
Claude Sonnet 5
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
Models overview
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
Overview
System prompts
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
Choosing a model
Choosing the right model
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
Migration guide
Migrating to Claude Fable 5.1 and Claude Mythos 5.1
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