Claude Code Agent Teams
Master parallel AI collaboration with agent teams. Learn to coordinate multiple Claude instances for complex debugging, code reviews, and cross-layer development.
Why take this course?
Unlock the power of parallel AI collaboration. When production is down and you need answers in minutes, not hours, agent teams let you investigate multiple hypotheses simultaneously. Learn to coordinate multiple Claude instances, implement competing hypotheses debugging, and orchestrate complex cross-layer development. From setup to advanced patterns, this course gives you the skills to leverage team-based AI for research, review, and development at scale.
Course Modules
Learning Goals
- Understand when and why to use agent teams vs single sessions or subagents
- Identify tasks that benefit from parallel exploration
- Distinguish between subagents and agent teams
Concept Card Preview
Visuals, diagrams, and micro-interactions you'll see in this module.
Sarah's Friday Deadline
It's 2 PM on Friday. Sarah's team lead just announced: Production is down.
The error could be anywhere—the frontend…
The Sequential Investigation Trap
Sarah's problem isn't unique. When bugs strike, we face what psychologists call "anchoring bias"—the tendency to fix…
Enter Agent Teams: Parallel Minds
Sarah discovers Agent Teams—a way to coordinate multiple Claude Code instances working together.
She creates a team…
Learning Goals
- Understand the three-layer architecture of agent teams
- Learn how teammates share information through the mailbox system
- Know where team configuration and tasks are stored
- Understand context boundaries between lead and teammates
Concept Card Preview
Visuals, diagrams, and micro-interactions you'll see in this module.
The Three Components of Every Team
When you create an Agent Team, you're not just spawning extra Claude instances. You're orchestrating three distinct comp…
How the Task List Coordinates Work
The shared task list is the heartbeat of team coordination. Here's how it works:
Task States:
- Pending: Create…
The Mailbox: Direct Communication
Unlike subagents that only report back to the caller, Agent Team teammates can message each other directly through the m…
Learning Goals
- Configure display modes (in-process vs split panes)
- Create your first agent team with proper prompts
- Navigate between teammates and communicate effectively
- Understand task claiming and assignment
Concept Card Preview
Visuals, diagrams, and micro-interactions you'll see in this module.
Enabling Agent Teams
Agent Teams are experimental and disabled by default. Before you can create your first team, you need to enable them:
*…
Creating Your First Agent Team
Creating an agent team is simple—just describe what you want in natural language:
I'm designing a CLI tool that hel…
Choosing Your Display Mode
Agent Teams support two ways to display teammates:
1. In-Process Mode (Default) All teammates run inside your main…
Learning Goals
- Master the competing hypotheses pattern for debugging
- Implement plan approval workflows for high-risk changes
- Use delegate mode for pure orchestration
- Apply quality gates with hooks
Concept Card Preview
Visuals, diagrams, and micro-interactions you'll see in this module.
The Competing Hypotheses Pattern
When debugging complex issues, a single investigator tends to find one plausible explanation and stop looking. This is a…
Plan Approval: Quality Gates for Complex Work
For complex or risky tasks, you can require teammates to get approval before implementing. This creates a checkpoint whe…
Delegate Mode: Pure Orchestration
By default, the lead might start implementing tasks itself instead of waiting for teammates. Delegate mode prevents…
Learning Goals
- Understand token cost implications of agent teams
- Know the hard limitations and how to work around them
- Apply battle-tested best practices
- Properly clean up teams when finished
Concept Card Preview
Visuals, diagrams, and micro-interactions you'll see in this module.
Understanding Token Costs
Agent Teams use significantly more tokens than a single session. Here's why:
The Math:
Each teammate is a **full C…
Hard Limitations to Know
Agent Teams are experimental. These are the current hard limitations:
**1. No Session Resumption (In-Process Teammates)…
Battle-Tested Best Practices
Learn from teams that have succeeded (and failed):
1. Give Teammates Enough Context Teammates load CLAUDE.md and pr…