Building with the Claude API
Go from your first API call to building tool systems, RAG pipelines, MCP servers, and agentic workflows — all in working Python code.
This course is for software engineers who want to integrate Claude into production applications. You should be comfortable writing Python and working with APIs. No prior experience with LLMs or Claude is required.
Course orientation and expectations.
1 lessons
The Claude model family and how to choose the right model.
1 lessons
API fundamentals: requests, multi-turn conversations, system prompts, temperature, streaming, and structured output.
13 lessons
Build automated evaluation pipelines with model-based and code-based graders.
8 lessons
Four systematic techniques for improving prompt quality, measured with eval scores.
7 lessons
Give Claude access to real-time data through custom tools, from schema design to multi-turn tool loops.
13 lessons
Build a complete RAG pipeline with semantic search, BM25 lexical search, and reciprocal rank fusion.
7 lessons
Extended thinking, image/PDF support, citations, prompt caching, and code execution.
9 lessons
Build MCP servers and clients using FastMCP: tools, resources, and prompts.
12 lessons
Effective development workflows with Claude Code and extending it with MCP servers.
4 lessons
Four workflow patterns and when to choose workflows vs agents for production reliability.
8 lessons
Comprehensive assessment covering all course modules.
1 lessons
Skills summary, next steps, and suggested projects.
1 lessons
No. The course starts from your first API call and builds up systematically. You should be comfortable with Python and REST APIs, but no AI/ML background is required.
You'll build a multi-turn chat system, a prompt evaluation pipeline, a complete tool use system (reminder app), a hybrid RAG pipeline, an MCP server and client, and learn to design agentic workflows.
The course contains 56 lessons across 13 modules. Most learners complete it in 6-8 hours of focused study, but you can work through it at your own pace.
Yes. The Introduction module is free so you can get a feel for the course structure and teaching style before purchasing.
Yes. You'll need an Anthropic API key for the hands-on exercises. The course walks you through obtaining one. Some modules also use VoyageAI for embeddings (free tier available).