Intermediate
Claude Code Subagents: Multi-Agent Orchestration
Go beyond single-session workflows. Learn to design, build, and coordinate teams of specialized AI agents — from your first custom subagent to production-grade multi-agent pipelines using the Claude Agent SDK.
01
What Are Subagents and Why They Change Everything
›
02
Creating Your First Custom Subagent
›
03
The Orchestrator-Worker Pattern
›
04
Parallel Fan-Out: Running Multiple Agents at Once
›
05
Fork Subagents: When to Share Context vs. Start Fresh
›
06
Controlling Tools, Permissions, and Isolation per Agent
›
07
Preloading Skills into Your Subagents
›
08
Connecting MCP Servers to Individual Agents
›
09
Agent Lifecycle Hooks: Automating Around Your Agents
›
10
Hierarchical Pipelines: Agents That Spawn Agents
›
11
Agent Teams: Agents That Communicate With Each Other
›
12
Monitoring and Debugging Multi-Agent Systems
›
13
Giving Your Subagents Persistent Memory
›
14
The Claude Agent SDK: Building Programmatic Agent Applications
›
15
Building a Production Multi-Agent Pipeline
›