Compiled from a deep-dive walkthrough covering intent understanding, task decomposition, reasoning patterns (ReAct, Plan-and-Execute, Reflection, Tree of Thought, Self-Consistency), planning graphs vs. prompts, the 3-tier memory system, the reasoning-engine decision loop, and Anthropic’s research on Claude’s internal “JSpace” — with added code examples and real-world context for clarity SECTION 0: Series Context & Recommended Learning […]

Compiled from a hands-on architecture + coding walkthrough covering the full system design, project folder structure, environment setup, the LLM Factory pattern, Chapter 1 (Basic Agent) and Chapter 2 (Skill Agent) — with added code examples and real-world context for clarity SECTION 1: The Big Picture — What’s Being Built Q1: What is the overall […]

Compiled from a hands-on coding walkthrough building a dynamic “Skill Selection” system with LangGraph — covering state definition, route/load/call-model nodes, dynamic prompt assembly, graph wiring, and Langfuse observability — with added code examples and real-world context for clarity SECTION 1: Chapter Goal & When to Use LangGraph Q1: What is the overall goal of this […]

Compiled from a hands-on coding walkthrough building 3 basic tools (Calculator, Get Time, Word Count) from scratch, registering them, binding to a model, building a tool-enabled StateGraph, and observing execution via Langfuse — with added code examples and real-world context for clarity SECTION 1: Chapter Goal & Setup Q1: What is the overall goal of […]

Compiled from a hands-on demo walkthrough progressively building up agent complexity: Bare LLM → Tool Calling → RAG → MCP → Memory/State → Supervisor → Hierarchical → Peer-to-Peer → Pipeline → Parallel → Reflection/Critique → Full Enterprise Pattern — with added real-world examples and code illustrations SECTION 0: The Big Picture — Progressive Complexity Q1: […]

Compiled from a hands-on coding walkthrough covering project structure, document loaders, token-based chunking strategy, embeddings, Chroma vector store, retrievers, and RAG tools — with added code examples and real-world context for clarity SECTION 1: Project Overview & Goals Q1: What is the overall goal of this hands-on session? A: To build a complete RAG (Retrieval-Augmented […]

Compiled from a detailed walkthrough of 20+ chunking strategies for building production RAG systems, with metadata filtering, and illustrated with added real-world/technical examples for clarity SECTION 0: Why Chunking Matters (Setup) Q1: Why does chunking strategy matter so much for RAG systems? A: Whether you’re processing a single PDF, thousands of PDFs, or millions of […]