LangChain & Agent Building

A linear, one-concept-per-lesson path through LangChain and agent building, from your first API call to a local research agent. 35 lessons · 3 tiers.

Prerequisites: Comfortable writing basic Python (functions, imports, running a script). This teaches AI/LangChain concepts, not coding.

Lessons use Google's Gemini free tier, not OpenAI or Anthropic: both require prepaid API credits, a separate account from their consumer chatbot subscriptions (ChatGPT Plus, Claude Pro don't include API access). Gemini's free tier removes that cost barrier for learning. Lesson 11 covers LangChain's provider-agnostic model interface, the same pattern that lets you swap in a self-hosted open-weight model (for example via Ollama) instead of a cloud API, if you'd rather run everything locally.

Built on LangChain, the open-source framework this course teaches.