What problem does it solve?
Provides a single, opinionated reference for integrating Anthropic Claude models and the Agent SDK into applications so teams avoid trial-and-error across languages, streaming, tool use, and agent workflows.
Core Features & Use Cases
- Language detection and curated, language-specific examples for Python, TypeScript, Java, Go, Ruby, C#, and PHP.
- Defaults and best practices for model selection, adaptive thinking, streaming, and long-output handling.
- Tooling patterns: beta tool runners, manual agentic loops, server-side tools (code execution, web search, web fetch), and Files API usage.
- Prompt caching, compaction, structured outputs, and error-handling guidance to build robust, production-grade integrations.
- Examples and patterns for batch processing, token counting, and MCP / Agent SDK usage for agents that need file/web/terminal access.
Quick Start
Ask for language-specific Claude API examples, for example: "Show me Python examples to call the Claude API with streaming, adaptive thinking, tool use, and prompt caching."