Claude Code Fundamentals
How an agentic CLI coding tool actually works, turn by turn
Learn what makes Claude Code an agentic tool rather than an autocomplete engine: the read-act-observe loop, the built-in tools it uses to explore and change your codebase, the permission modes that govern its autonomy, and where its configuration lives. By the end you'll be able to trace exactly what happens, tool call by tool call, when you ask it to fix a bug.
Practice questions (12)
-
View →
Tracing the Agentic Loop Through a Real Task
Beginner · Free -
View →
Choosing a Permission Mode for a New Contributor
Intermediate · Free -
View →
Why Edit Failed and What It Reveals About the Tools
Intermediate · Free -
View →
Scoping Permission Rules Across a Team
Intermediate · Free -
View →
Diagnosing Why Two Prompts Produce Different Quality Outcomes
Beginner · Free