Learn Claude — from zero to production.

Two tracks: Foundations, then Capstones

☺ Like you're 10: First you learn the pieces, one at a time. Then you watch six different teams put all the pieces together to solve a real job.

The course has 21 Foundation lessons, meant to be read in order — from your first API call through prompting, the Messages API, tool use, caching, RAG, agent-building patterns, MCP, Claude Code, safety, evaluation, and production. Then six Capstone projects in different domains, each contrasting a naive approach against one or more production-grade patterns straight out of Anthropic's own Building Effective Agents playbook.

Meet the Claude Crew

☺ Like you're 10: To make the big ideas stick, this course is taught by a team of animal friends. Each one is an expert at one job — so the moment the octopus shows up, you'll know it's time to talk about running several agents at once.

Every concept in this course has a recurring character who is that idea — 🦉 Professor Owl teaches, 🦊 Foxy asks the questions, 🐘 Ellie remembers, 🦫 Benny builds, 🐙 Olly runs the agents, 🐢 Timmy checks the work, 🐿️ Nutty gathers the data, and 🐦 Pip carries the messages — plus a dedicated guide for each capstone domain. Watch for the "Your host for this topic" strip and the little "🎬 At the Claude Crew" scenes in each lesson.

Meet the full roster and see how it works → The Claude Crew

Six capstones, six domains

☺ Like you're 10: A capstone is the last, biggest LEGO build after you've learned all the pieces — it's where you see the whole thing actually work.

Each capstone compares 2-3 different implementation methodologies in a real domain, names the exact pattern from Building Effective Agents it relies on, and calls out the domain-specific risks and guardrails a real deployment would need.

The one mental model that makes everything click

☺ Like you're 10: Picture a dial that goes from "I write the whole plan" to "I tell Claude the goal and it figures out the steps." You turn the dial further only once you trust it with that job.

Before any feature, internalize this from Anthropic's own Building Effective Agents: a Claude-based system is not one thing — it is a spectrum of autonomy. A workflow is a predefined code path where you decide what happens next; an agent is Claude dynamically directing its own process and tool use. Every capability in this course sits somewhere on the line above, and the guidance is consistent throughout: start with the simplest thing that works — often a single well-crafted prompt — and add complexity only when a simpler solution demonstrably falls short.

What's inside

☺ Like you're 10: The lessons are stacked like levels in a game — each one uses what you learned in the level before, so you keep getting stronger instead of starting over.

…plus a self-check quiz, spaced-repetition flashcards, and the full Foundations and Capstones tracks in the sidebar.