Agent Engineer Course
A course for software engineers who want to understand what AI agents are, how they work, and how to build them.
Course overview
Section titled “Course overview”This course is split into three parts:
- Part 1: Fundamentals - Understand the core concepts behind AI agents. These lessons are platform-agnostic and focused on building your mental model.
- Part 2: Building and Shipping - Put those fundamentals into practice using Claude Code, the Anthropic API through your company’s LiteLLM proxy, and the Claude Agent SDK.
- Part 3: Deep Dives - Go deeper on specific topics that matter for real-world agent development.
Prerequisites
Section titled “Prerequisites”- Basic Python knowledge (functions, classes, HTTP requests)
- Claude Code installed and working, and an API key for your company’s LiteLLM proxy (from your internal developer portal)
- Familiarity with REST APIs and JSON
About this course
Section titled “About this course”The course content was written by Addy Osmani and originates from addyosmani/agent-engineer, also published at addyosmani.com/agents. The Starlight site setup was created by Ivar Soares Urdalen in ivarurdalen/agent-engineer-course.
This edition adapts the course for engineers building with the Claude stack: Claude Code as the daily driver, the Anthropic API through your company’s LiteLLM proxy, and the Claude Agent SDK - along with the production tool choices (FastMCP, LangGraph, Langfuse, and friends) introduced in Lesson 12. It is licensed under the Apache 2.0 License.