Learn how AI agents work by building them yourself. Join Roy for hands-on Python development with the Anthropic Python SDK, tools, workflows, evaluations, MCP and RAG.

Building AI Agents — Develop an AI agent from scratch using the Anthropic Python SDK. Understand how its core components work together.
Tool Use — Enable your agent to call external tools and APIs to carry out tasks beyond generating text.
Deterministic Workflows — Build AI workflows with predefined execution steps and explicit logic.
Non-deterministic Workflows — Build agentic workflows that make decisions and dynamically select an execution path.
Evaluations (Evals) — Test and evaluate agent performance, accuracy and reliability.
MCP (Model Context Protocol) — Connect AI agents to external tools and systems through MCP.
RAG (Retrieval-Augmented Generation) — Retrieve external knowledge and provide it to an LLM to support more accurate, context-informed answers.
This workshop focuses on developing AI agents and LLM-powered applications from scratch using Python and the Anthropic Python SDK. You will write code yourself to understand the underlying development principles.
Workshop content is provided by Anthropic and is based on Claude Certified Architect – Foundations. This is a development workshop; Claude Code, Codex and other AI coding tools will not be used.
将 Claude Agent Workshop 分享给朋友


