BEGINNER · 7 MODULES · 33 LESSONS
How Coding Agents Work
Understand how coding agents think, act, and fail so you can direct them with judgment in any tool, and build a small one to see how it works inside.
- For you if
- You use a coding agent every day, or are about to start, and want to understand what goes on inside.
- By the end
- You'll know how a model becomes an agent, when to trust its output, and how to work by researching, planning, executing, and validating.
- You need
- Basic programming, an editor, a terminal, and git. For the final project, an Anthropic or OpenAI API key.

Curriculum
01The Paradigm Shift: AI in Software Development
02How LLMs Work (what you need to know as a developer)
04The agent's toolbox: how they interact with your code
- Module 4: The Agent's Toolbox: How They Interact with Your Code
- File Operations, Shell, and Web Search: The Three Categories of Tools
- How Agents "See" Your Codebase
- Context Management: Large Projects and the Context Window Limit
- Configuration and Permissions: CLAUDE.md, .cursor/rules, AGENTS.md, and Sandboxing
06The fundamental workflow: Research → Plan → Execute → Validate
- Module 6: The Fundamental Workflow: Research → Plan → Execute → Validate
- Research → Plan → Execute → Validate: The Fundamental Workflow
- Workflow Variants: PRD → Plan → Todo → Code, Spec-First, Explore → Plan → Code
- Verification: The Step Everyone Skips
- Common Anti-Patterns: What NOT to Do with Coding Agents
07Project: Build a mini coding agent and analyze its behavior
Reviews
What students say
These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.
No approved reviews yet.
Be the first to share your experience!