Part VI: Agentic AI

Building autonomous AI agents that use tools, plan multi-step tasks, and collaborate in multi-agent systems.

"We build our tools, and then our tools build us."

Marshall McLuhan

Part Overview

Part VI covers the complete landscape of agentic AI: from single-agent foundations through multi-agent orchestration to specialized agents and production safety. You will build agents that perceive, reason, and act autonomously; connect them to tools and external systems through standardized protocols; compose them into multi-agent teams; specialize them for code generation, web automation, and domain-specific tasks; and deploy them safely into production with observability, testing, and cost controls.

Chapters: 5 (Chapters 22 through 26). These chapters draw on every preceding part and prepare you for the application, evaluation, and production topics that follow.

Big Picture

Moving beyond single-turn question answering, Part VI covers the rapidly evolving field of AI agents: systems that plan, use tools, collaborate with other agents, and take actions in the real world. This part connects everything you have learned so far into autonomous, production-ready systems.

Code generation agents, browser agents, computer use agents, research agents, and domain-specific agent design patterns.

What Comes Next

Continue to Part VII: AI Applications, where we extend LLM capabilities to vision, audio, and document understanding, then survey major application domains.