Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Part 2: Core Capabilities

🧠 Systematically master all the core technical capabilities needed to build Agents — from tool calling to reinforcement learning training.

This is the most substantial part of the book, containing 7 chapters that cover the complete capability progression chain for Agents.

ChapterContentAnalogy
Chapter 4 Tool CallingFunction Calling, custom toolsThe Agent's "hands"
Chapter 5 Memory SystemShort-term / long-term / working memoryThe Agent's "brain"
Chapter 6 Planning & ReasoningReAct, task decomposition, reflectionThe Agent's "thinking"
Chapter 7 RAGDocument retrieval, vector databasesThe Agent's "knowledge base"
Chapter 8 Context EngineeringWindow management, attention budgetThe Agent's "information hub"
Chapter 9 Skill SystemSkill encapsulation, learning & discoveryThe Agent's "skill tree"
Chapter 10 Agentic-RLSFT, PPO, DPO, GRPOThe Agent's "self-evolution"

Capability Progression: Use tools → Remember → Think → Retrieve → Manage context → Encapsulate skills → Self-evolve


Start learning: Chapter 4: Tool Calling