Anthropic

Everything you need to know about Anthropic's Claude Certified Architect – Foundations (CCA-F) certification: exam structure, five domains, scenario types, and how to prepare for production-scale Claude application design.

Should you build a workflow or an agent? Learn the key differences, trade-offs, and when to use each approach for reliable AI-powered applications. Includes decision framework, hybrid patterns, and real-world examples.

Take your prompt caching implementation to the next level with advanced strategies, edge case handling, and production-ready patterns for high-volume applications.

When building MCP servers, you need a way to test your functionality without connecting to a full application. The Python MCP SDK includes a built-in browser-based inspector that lets you debug and test your server in real-time.

Resources in MCP servers allow you to expose data to clients, similar to GET request handlers in a typical HTTP server. They're perfect for scenarios where you need to fetch information rather than perform actions.

Learn when to let Claude figure out the steps instead of defining them yourself. Discover how to build powerful agents with simple, combinable tools that handle unpredictable tasks. Includes tool design principles and real-world examples.

Learn how MCP clients and servers work together by building a command-line chatbot. This hands-on tutorial demonstrates both sides of the MCP architecture through a practical document management system.

Stop using one-size-fits-all prompts. Learn how routing workflows categorize user requests and send them to specialized pipelines for better, more consistent results. Includes real-world examples and implementation best practices.

Learn how to build an MCP client that bridges your application logic with server capabilities. This tutorial covers the two-layer client architecture, implementing core methods, and testing the complete flow.

Resources in MCP allow your server to expose data that can be directly included in prompts, rather than requiring tool calls to access information. This creates a more efficient way to provide context to AI models like Claude.