The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

A 603-page practitioner's reference covering the full stack of building autonomous AI systems, from transformer internals through production deployment. The survey's organizing thesis is that building effective agentic systems demands understanding every layer of the pipeline.

Part 1 covers the LLM substrate: transformer architecture, GPU systems, training and fine-tuning (SFT, LoRA, MoE), model compression, and inference optimization. It then moves through alignment and reasoning — RLHF, PPO, DPO and its variants, GRPO, reward modeling, and RL for large reasoning models including chain-of-thought and test-time scaling.

Part 2 covers agentic systems: trajectory-based RL for agent training, RAG and Agentic RAG, memory systems, harness design, and a taxonomy of agent design patterns. It surveys the Model Context Protocol (MCP), agent skills and tool use, the Agent-to-Agent (A2A) protocol, and multi-agent architectures (centralized, decentralized, hierarchical). Closing chapters cover agent development frameworks, agentic UI, evaluation methodology, and production deployment.

Each chapter pairs theoretical foundations with implementation guidance, code examples, and references. Published June 2026 under CC BY-SA 4.0.