AI Agents Learning Path
Understand how AI agents plan, use tools, and remember context, then learn to design and ship your own.
Curated Lessons6 Modules
What Is an AI Agent? A Beginner's Guide to How Agents Work
Learn what an AI agent is, how it differs from a chatbot and a workflow, what parts it is made of, where agents are used today, and when you should not build one.
How LLMs Work: Tokens, Context Windows and Embeddings for Agent Builders
Learn the parts of a large language model that matter when you build AI agents: tokens, context windows, how a reply is generated, why long conversations cost more, and what embeddings are for.
Choosing and Configuring a Model for Your AI Agent
Learn how to pick a model for an agent and set it up well: temperature and top-p, stop reasons, reasoning and effort, open versus closed models, streaming, token pricing, and when to fine-tune instead of prompt.
The Agent Loop Explained: Perceive, Reason, Act, Observe
Learn how the agent loop works step by step: how the model asks for a tool, how your code runs it and reports back, what a turn is, what ends the loop, and how to write the loop yourself in a few lines of Python.
Workflows or Agents? How to Decide What to Build
Learn how to choose between a single model call, a workflow and an agent. A ladder of complexity, a four-question checklist, real cost numbers, worked examples, and why you should start simple and measure.
Build Your First AI Agent From Scratch in Python
Build a small working AI agent in Python with direct Claude API calls. Set up your key, define two tools, write the loop, print every step, protect against a bad file path, and stop safely.