Building Agentic AI Systems

Part I · Chapter 00 · 4 sections · 47 min

Essential knowledge and environment setup for building AI agents

1. 0.1What You Need to Know10m
2. 0.2Development Environment Setup15m
3. 0.3API Keys and Configuration10m
4. 0.4Project Structure Overview12m

Part I · Chapter 01 · 5 sections · 70 min

Understanding the shift from chatbots to autonomous agents

1. 1.1From Chatbots to Agents12m
2. 1.2What Makes an AI Agent15m
3. 1.3The Agent Landscape in 202518m
4. 1.4Use Cases and Applications15m
5. 1.5Book Roadmap and Projects10m

Part I · Chapter 02 · 6 sections · 101 min

Core components and design patterns of AI agents

1. 2.1The Agent Loop: Perceive-Reason-Act15m
2. 2.2Core Components Overview18m
3. 2.3LLM as the Reasoning Engine20m
4. 2.4Tool Integration Architecture18m
5. 2.5Memory and State Management15m
6. 2.6Planning and Execution15m

Part II · Chapter 03 · 7 sections · 115 min

Deep dive into Anthropic's agentic coding assistant

1. 3.1Claude Code Architecture Overview15m
2. 3.2The Terminal-First Philosophy12m
3. 3.3Agentic Search and Context Gathering18m
4. 3.4Tool System: Read, Write, Execute20m
5. 3.5CLAUDE.md: Context Engineering15m
6. 3.6The Feedback Loop Pattern15m
7. 3.7Claude Agent SDK Deep Dive20m

Part II · Chapter 04 · 6 sections · 95 min

Understanding OpenAI's sandboxed coding agent

1. 4.1Codex Architecture Overview15m
2. 4.2Sandboxed Cloud Execution18m
3. 4.3Dynamic Reasoning with o320m
4. 4.4AGENTS.md Configuration12m
5. 4.5Multi-Platform Agent Design15m
6. 4.6Safety and Verification15m

Part II · Chapter 05 · 5 sections · 81 min

Google's multimodal agent architecture

1. 5.1Gemini Multimodal Architecture18m
2. 5.2Native Multimodality Design15m
3. 5.3Controllable Reasoning Depth15m
4. 5.4Gemini Code Assist Agent Mode18m
5. 5.5Integration with Open Source Frameworks15m

Part III · Chapter 06 · 5 sections · 100 min

Reasoning and Acting in synergy

1. 6.1Understanding ReAct15m
2. 6.2Thought-Action-Observation Cycle18m
3. 6.3Implementing ReAct from Scratch25m
4. 6.4ReAct vs Chain-of-Thought12m
5. 6.5Building a ReAct Agent30m

Part III · Chapter 07 · 7 sections · 125 min

Connecting agents to the real world

1. 7.1Why Agents Need Tools12m
2. 7.2Function Calling Fundamentals18m
3. 7.3Designing Effective Tools20m
4. 7.4Tool Schemas and Validation15m
5. 7.5Implementing Tool Execution25m
6. 7.6Error Handling and Retries15m
7. 7.7Advanced Tool Patterns20m

Part III · Chapter 08 · 6 sections · 112 min

The universal standard for tool integration

1. 8.1What is MCP12m
2. 8.2MCP Architecture Deep Dive20m
3. 8.3Building MCP Servers25m
4. 8.4Building MCP Clients20m
5. 8.5MCP Security Considerations15m
6. 8.6Integrating MCP with Agents20m

Part III · Chapter 09 · 7 sections · 140 min

Building persistent and contextual memory

1. 9.1Why Memory Matters12m
2. 9.2Short-term vs Long-term Memory15m
3. 9.3Vector Databases for Memory20m
4. 9.4RAG for Contextual Retrieval25m
5. 9.5Conversation Memory Management18m
6. 9.6Knowledge Graphs for Agents20m
7. 9.7Building a Memory System30m

Part III · Chapter 10 · 6 sections · 103 min

How agents break down and solve complex tasks

1. 10.1Task Decomposition15m
2. 10.2Hierarchical Planning18m
3. 10.3Self-Reflection and Correction15m
4. 10.4Chain-of-Thought Prompting12m
5. 10.5Tree of Thoughts18m
6. 10.6Implementing a Planner Agent25m

Part IV · Chapter 11 · 6 sections · 110 min

Step-by-step implementation of a functional agent

1. 11.1Agent Design Decisions15m
2. 11.2The Agent Core Loop20m
3. 11.3Adding Tools25m
4. 11.4Implementing Memory20m
5. 11.5Error Handling and Recovery15m
6. 11.6Testing Your Agent15m

Part IV · Chapter 12 · 7 sections · 153 min

Create an agent that writes and executes code

1. 12.1Coding Agent Architecture15m
2. 12.2File System Tools20m
3. 12.3Code Execution Sandbox25m
4. 12.4Git Integration18m
5. 12.5Test-Driven Agent Development20m
6. 12.6Debugging and Iteration Loop20m
7. 12.7Complete Coding Agent Implementation35m

Part IV · Chapter 13 · 7 sections · 131 min

Create an agent that searches, reads, and synthesizes information

1. 13.1Research Agent Architecture15m
2. 13.2Web Search Integration18m
3. 13.3Web Scraping and Extraction20m
4. 13.4Document Processing18m
5. 13.5Information Synthesis15m
6. 13.6Source Citation and Verification15m
7. 13.7Complete Research Agent Implementation30m

Part V · Chapter 14 · 6 sections · 103 min

When and how to use multiple agents

1. 14.1Why Multi-Agent Systems12m
2. 14.2Architecture Patterns Overview18m
3. 14.3Supervisor Pattern20m
4. 14.4Peer-to-Peer Collaboration15m
5. 14.5Hierarchical Orchestration18m
6. 14.6Shared State and Communication20m

Part V · Chapter 15 · 7 sections · 136 min

Graph-based multi-agent orchestration

1. 15.1LangGraph Fundamentals15m
2. 15.2Nodes, Edges, and State20m
3. 15.3Building Cyclic Graphs18m
4. 15.4Conditional Routing15m
5. 15.5Human-in-the-Loop Patterns18m
6. 15.6Persistence and Checkpointing15m
7. 15.7Building a LangGraph Multi-Agent System35m

Part V · Chapter 16 · 6 sections · 113 min

Role-based multi-agent orchestration

1. 16.1CrewAI Architecture15m
2. 16.2Agents, Tasks, and Crews18m
3. 16.3Role-Based Agent Design20m
4. 16.4Sequential vs Hierarchical Processes15m
5. 16.5Tool Sharing and Delegation15m
6. 16.6Building a CrewAI Application30m

Part V · Chapter 17 · 6 sections · 87 min

Fully autonomous agent architectures

1. 17.1AutoGPT Architecture15m
2. 17.2The Self-Prompting Loop18m
3. 17.3Goal Decomposition15m
4. 17.4Iterative Refinement15m
5. 17.5Limitations and Challenges12m
6. 17.6When to Use Autonomous Agents12m

Part VI · Chapter 18 · 7 sections · 123 min

Building safe and controllable agents

1. 18.1The Agent Safety Challenge12m
2. 18.2Input Validation and Sanitization18m
3. 18.3Output Filtering and Controls15m
4. 18.4Prompt Injection Defense20m
5. 18.5Sandboxing and Isolation18m
6. 18.6Human-in-the-Loop Controls15m
7. 18.7Implementing Guardrails25m

Part VI · Chapter 19 · 6 sections · 95 min

Understanding what your agents are doing

1. 19.1Why Observability Matters12m
2. 19.2Logging Agent Actions15m
3. 19.3Tracing Agent Workflows18m
4. 19.4Metrics and Dashboards15m
5. 19.5Debugging Agent Failures20m
6. 19.6Cost Monitoring and Optimization15m

Part VI · Chapter 20 · 6 sections · 103 min

Measuring agent performance and reliability

1. 20.1Agent Evaluation Challenges12m
2. 20.2Industry Benchmarks Overview18m
3. 20.3SWE-bench and Coding Evaluations15m
4. 20.4Building Custom Evaluation Suites25m
5. 20.5A/B Testing Agents15m
6. 20.6Continuous Evaluation Pipelines18m

Part VI · Chapter 21 · 6 sections · 96 min

Taking agents from prototype to production

1. 21.1Production Architecture Patterns15m
2. 21.2Scaling Agent Systems18m
3. 21.3Queue-Based Agent Processing15m
4. 21.4Error Recovery and Resilience18m
5. 21.5API Design for Agent Services15m
6. 21.6Deployment Strategies15m

Part VII · Chapter 22 · 5 sections · 83 min

Mastering prompts for agent behavior

1. 22.1System Prompts for Agents15m
2. 22.2Persona and Role Engineering15m
3. 22.3Few-Shot Examples for Tools18m
4. 22.4Dynamic Prompt Assembly20m
5. 22.5Context Window Management15m