Subagents are one of the most practical ways to get more out of longer Claude Code sessions. They let you delegate tasks to isolated assistants that do their work separately and return just the information you need — keeping your main context window clean and your conversations focused.
Introduction to subagents
Decompose complex tasks across parallel Claude subagents and orchestrate them deterministically.
4 lessons45 min
What you’ll learnBy the end of this course, you’ll be able to
- Explain how subagents work: how Claude Code spins up a separate context window, how inputs flow in, and how summaries come back
- Create custom subagents with the /agents command for workflows like code review and documentation generation
- Design reliable subagents with structured output formats, obstacle reporting, and limited tool access
- Decide when subagents help most and recognize the common anti-patterns to avoid