Building AI Agents with the Claude Agent SDK

From Fundamentals to Production Deployments

Introduction: The Agent Revolution

1. What Are AI Agents and Why They Matter
2. From Claude Code CLI to Agent SDK
3. What You Will Build
4. How to Read This Book

Chapter 1: AI Agent Fundamentals

1. The Anatomy of an AI Agent
2. Tool Use and Function Calling
3. The Agent Loop
4. Memory Architectures for Agents
5. Planning and Reasoning Patterns
6. Agent vs. Workflow: When to Use Each
7. Chapter Summary
8. Exercises
9. Interview Questions

Chapter 2: SDK Architecture and Environment Setup

1. The SDK Stack: Client SDK vs. Agent SDK
2. Installation and Authentication
3. Project Configuration and CLAUDE.md
4. The Subprocess Model
5. Multi-Language Support: Python and TypeScript
6. Chapter Summary
7. Exercises
8. Interview Questions

Chapter 3: Core APIs and the Agent Loop

1. The query() Function
2. ClaudeSDKClient for Multi-Turn Conversations
3. Message Types and Lifecycle
4. Turn Management and Budget Controls
5. Session Persistence and Resumption
6. The Agent Loop in Action: First Complete Example
7. Chapter Summary
8. Exercises
9. Interview Questions

Chapter 4: Built-In Tools and Tool Use

1. File Operations: Read, Write, Edit
2. Search and Discovery: Glob, Grep
3. Command Execution: Bash and Monitor
4. Web Tools: WebSearch and WebFetch
5. User Interaction: AskUserQuestion
6. Permission Modes and Tool Access Control
7. Parallel vs. Sequential Tool Execution
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 5: Custom Tools and MCP Integration

1. Defining Custom Tools in-Process
2. Tool Result Formats
3. MCP Server Integration
4. Tool Search and Context Optimization
5. Building a Complete Custom Tool: Weather Service Example
6. Chapter Summary
7. Exercises
8. Interview Questions

Chapter 6: Memory Systems and Context Management

1. The Context Window: Sizes, Limits, and Budgets
2. Automatic Context Compaction
3. CLAUDE.md: Project-Level Memory
4. The Memory Tool
5. Retrieval-Augmented Generation with Agents
6. Context Optimization Strategies
7. Chapter Summary
8. Exercises
9. Interview Questions

Chapter 7: Prompt Engineering for Agents

1. System Prompts vs. User Prompts in Agent Context
2. Writing Effective Agent System Prompts
3. CLAUDE.md Mastery
4. XML Structuring and Few-Shot Examples
5. Extended Thinking and Effort Levels
6. Prompt Caching Across Sessions
7. Chapter Summary
8. Exercises
9. Interview Questions

Chapter 8: Subagents and Multi-Agent Systems

1. Why Subagents: Context Isolation and Parallelism
2. Programmatic AgentDefinition
3. Automatic vs. Explicit Invocation
4. Subagent Inheritance and Isolation
5. Detecting and Resuming Subagents
6. Dynamic Workflows for Large-Scale Orchestration
7. Common Multi-Agent Patterns
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 9: Hooks and Human-in-the-Loop Patterns

1. Hook Architecture and Execution Pipeline
2. Lifecycle Events Reference
3. Matcher Patterns and Filtering
4. Blocking and Transforming Tool Calls
5. Human Approval Workflows
6. Async Hooks for Observability
7. Anti-Patterns: Hook Pitfalls
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 10: Structured Outputs and Data Extraction

1. Why Structured Outputs Matter
2. Defining Output Schemas
3. Multi-Tool Structured Extraction
4. Error Handling for Schema Validation
5. Best Practices and Anti-Patterns
6. Chapter Summary
7. Exercises
8. Interview Questions

Chapter 11: Testing, Debugging, and Evaluation

1. The Challenge of Testing Agents
2. Unit Testing Tools and Hooks
3. Promptfoo Integration
4. MLflow Tracing and Evaluation
5. Debugging Strategies
6. Building Evaluation Datasets
7. Continuous Evaluation in CI/CD
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 12: Observability and Performance Optimization

1. The Three Signals: Metrics, Traces, Logs
2. OpenTelemetry Integration
3. Cost Tracking and Budget Management
4. Performance Optimization Strategies
5. Prompt Caching for Cost Reduction
6. Observability Tooling Comparison
7. Redacting PII and Secrets from Telemetry
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 13: Security and Sandboxing

1. The Agent Threat Model
2. Built-In Security Features
3. Sandbox Runtime: bubblewrap and sandbox-exec
4. Container Isolation Strategies
5. Credential Management
6. Filesystem Security
7. Network Security
8. Defense in Depth Checklist
9. Chapter Summary
10. Exercises
11. Interview Questions

Chapter 14: Deployment, Scaling, and Production Operations

1. Hosting Patterns
2. Container Providers
3. Session Persistence in Production
4. Scaling Strategies
5. Multi-Tenant Isolation
6. Monitoring and Alerting in Production
7. Known Limitations and Workarounds
8. Chapter Summary
9. Exercises
10. Interview Questions

Chapter 15: Real-World Case Studies and Enterprise Architecture

1. Case Study: Automated Code Review Pipeline
2. Case Study: RAG-Powered Customer Support Agent
3. Case Study: Research Assistant with Parallel Subagents
4. Enterprise Integration Patterns
5. Managed Agents vs. Self-Hosted SDK
6. Comparison with Alternative Frameworks
7. The Future of Agent Development
8. Chapter Summary
9. Exercises
10. Interview Questions

Conclusion: Your Agent Journey Ahead

1. Key Takeaways
2. Building Your First Production Agent
3. The Evolving Landscape
4. Resources and Community

References