The Agentic AI book

Description

Welcome to the Leanpub Launch video for The Agentic AI book: From Language Models to Multi-Agent Systems https://leanpub.com/TheAgenticAIbook by Dr. Ryan Rad! 00:00 Introduction to The Agentic AI Book 00:16 Ryan Rad's background in AI, engineering, and education 01:31 How AI is changing who gets to build software 02:14 The rise of the "craft engineer" in the LLM era 03:03 Why learning modern AI has become so difficult 03:53 The problems with AI hype, fragmented content, and dense research 04:24 Why Ryan wrote The Agentic AI Book 05:02 Who the book is for (and who it isn't) 05:47 Understanding LLMs, RAG, and AI agents without framework lock-in 06:18 Why tools change but fundamentals endure 06:55 Staying relevant in an AI-driven future 07:38 Deep expertise as a competitive advantage 08:09 Experimenting with AI and finding where humans add value 08:50 Adapting professional skills in the age of AI 09:31 Closing remarks About the Book ⭐ Top-3 Bestseller in Deep Learning and Generative AI every single week since launch. ⭐ The Paradox of AI Today It’s never been easier to build an agent—and never been harder to understand why it works, why it fails, or how to make it production-ready. The barrier to entry has collapsed; the barrier to mastery has never been higher. The Agentic AI Book bridges that gap. This is the definitive guide to understanding the core components of AI agents and building systems that actually work in the real world. While others show you how to build agents in low-code environments and hope for the best, this book reveals why agents fail and how to fix them. 📖 Inside the Book Not surface-level tutorials. Not "vibes-based" prompting. Each section builds from first principles to complex orchestration, covering not just what these systems do, but how they work architecturally. Foundations: Master the Three-Layer Framework (Architecture, Training, Objective) to deconstruct any model, from n-grams to GPT-4o. Understand the death of Hard Logic, the rise of Learned Intuition, and the Scaling Laws that define the physics of modern AI. LLMs & VLMs: Diagnose the Reversal Curse, the Modality Gap, and Perception-Reasoning Dissociation in vision models. Learn why Inference-Optimal Overtraining means a smaller model can outperform a giant. Adaptation & Reliability: When prompts fail, renovate the weights. Master chunking strategies, the RAG Triad, LoRA/QLoRA, and the alignment frontier, DPO and GRPO, the secret sauce behind today's top reasoning models. Agent Architecture: Define autonomy through Control Flow with the 6 Levels of Agentic Autonomy. Apply Poka-Yoke principles to tool design via the ACI, and fight Context Rot with JIT Context and Attention Budget management. Multi-Agent Systems: Orchestrate agent societies using DAG-based task graphs and the AAI. Know when not to scale (the Complexity Tax), slash costs with Semantic Compression, and prevent deadlocks and runaway costs with Conflict Resolution Protocols. Production Reality (D2D): Replace hope with Reliability Engineering. Master Quantization and Speculative Sampling for efficient deployment. Implement guardrails, observability, and Security & Governance; and debug Agentic Race Conditions before they reach your users. 🚀 Progress & Roadmap The book is currently 92% complete. By joining now, you get immediate access to the core foundations and can influence the final chapters. Chapter 1: The AI Landscape ✓ Chapter 2: Language Models and Multimodal Intelligence ✓ Chapter 3: Building with Large Language Models ✓ Chapter 4: Agent Building Blocks ✓ Chapter 5: Multi-Agent Architectures & Design Patterns ✓ Chapter 6: Production-Ready Agentic AI (6.1-6.2✓ - 6.3-6.4 Coming Mid-June) Final Digital Edition: Late June 2026 💎 Join as a Founding Member Instead of a traditional "Early Bird" discount, for a limited-time I am inviting you to join as a Founding Member. Value-Based Pricing: To reward early supporters, the price grows with the book. While the final book will retail at (~$50), you can currently lock in the 92% version for as low as $20. Lifetime Access: Receive new chapters monthly, bonus content, and the final completed digital version in June at no extra cost. Exclusive Bonus Content: Includes access to the private code repository and real-world case studies. Amazon Print Discount: All Founding Members will receive a special discount code for the physical print version when it launches (est. June 2026). Ready to move beyond demo-grade agents to production-ready systems? Time is ticking! ⏳ The book is nearing completion this May, and this founding offer is only available for a limited time. Secure your lifetime access now before the price increases. 🕒 Learn more at book.ryanrad.org About the Author Dr. Ryan Rad is an AI researcher, professor, and industry advisor with over 15 years shaping how artificial intelligence is built, taught, and deployed. He holds faculty positions at Northeastern University and the University of British Columbia, where he has designed curricula and graduate programs in Machine Learning, Computer Vision, Generative AI, and Data Science—reaching thousands of students across six universities and online. His industry work spans research, engineering, and leadership at startups and tech giants including Microsoft, scaling AI solutions across 40 countries for Fortune 500 companies. A sought-after speaker with 50+ international talks and tens of top-tier peer-reviewed publications, Dr. Rad's research focuses on resource-efficient generative AI for edge deployment. He is the author of The Agentic AI Book—distilling years of building, teaching, and deploying AI into actionable insights—and shares AI perspectives on his YouTube channel. Thank you for watching, please like and leave a comment, we'd love to hear from you! Please Subscribe and Follow! YouTube: https://www.youtube.com/leanpub X: https://x.com/leanpub Instagram: https://www.instagram.com/leanpub Facebook: https://www.facebook.com/leanpub Create Your Own Leanpub Book! You can create your own book anytime here: https://leanpub.com/create/book Here's the tutorial showing how to write and publish a Leanpub book in your browser (it's free!): http://help.leanpub.com/en/articles/2932527-getting-started-writing-a-book-in-the-web-browser-writing-mode If you're a Leanpub author and you'd like to submit your own Launch video for us to publish, or if you'd like to record a Launch video with Len, please go here: https://leanpub.com/launch. #books #leanpublishing #selfpublishing #leanpub #writing #ai #computerscience #deeplearning #datascience #gpt #neuralnetworks #machinelearning