The Hitchhiker's Guide to Agentic AI

Part I — Foundations

• 1LLM Architecture and Optimization Methods
• 2Systems Foundations for LLMs
• 3Introduction to Reinforcement Learning

Part II — RL Methods for LLMs

• 4RL Foundations for Language Models
• 5PPO — Proximal Policy Optimization
• 6DPO — Direct Preference Optimization
• 7GRPO — Group Relative Policy Optimization
• 8Preference Optimization Variants
• 9Reward Model Training
• 10SFT Best Practices and Techniques
• 11System Architecture & Infrastructure at Scale
• 12LLM Agentic Training

Part III — Reasoning

• 13RL for Large Reasoning Models

Part IV — Evaluation

• 14LLM Evaluation

Part V — Agentic AI

• 15Introduction to Agentic AI
• 16RAG — Retrieval-Augmented Generation
• 17Memory Systems
• 18Orchestration
• 19Loop Engineering
• 20Design Patterns
• 21Environments and Benchmarks
• 22Model Context Protocol (MCP)
• 23Agent Skills
• 24A2A Communication
• 25Multi-Agent Systems
• 26Development Frameworks
• 27Agentic UI

Part VI — Assessment & Reference

• 28Quiz Questions & Detailed Answers
• 29Quick Reference
• 30Conclusion and Future Directions