Books

Agentic AI is everywhere, but what does it actually mean? This book cuts through the hype and explains how AI agents work, how they are built and where they can go wrong. Starting from the basics, it gives you a clear, practical understanding of the technology and what it takes to trust an agent in the real world.

Learn to design, build and govern agentic systems as you prepare for the Google Cloud Professional Agentic Architect exam. Study practical architectures and worked examples, then test your understanding with 100 original questions aligned with the public exam objectives.

AI can generate an answer. But can it safely take action?AI agents are changing software by giving intelligent systems the ability to plan, use tools, interact with external systems, and execute multi-step workflows.Moving from an impressive prototype to a dependable production system, however, requires much more than a powerful model.AI Agents & Agentic Workflows in Production explores the engineering principles behind production-grade agentic systems—from architecture and tool use to memory, planning, orchestration, evaluation, security, reliability, observability, scalability, governance, and continuous operation.Learn how to build agents that don't just act—but act reliably, safely, measurably, and under control.

Build Claude into a reliable specialist for your domain. The Claude Skills Handbook takes you from the first idea through architecture, implementation, testing, security, deployment and monitoring, with practical patterns and working examples throughout. Learn how to build Skills that scale, stay maintainable and work in the real world.

Build AI agents that actually hold up in production. This practical guide covers agent architecture, tool use, multi-agent systems, security, reliability, observability and operations, with working code throughout. Learn how to build agents that are dependable, cost-aware and ready for the real world.

Your manager calls you into a meeting. Everyone is cheerful. The Head of Sales is there. “We heard AI is really useful for boosting productivity. We’d love to explore how it can help us in Sales.” Your manager agrees. “This is the perfect pilot. Please give us a concept until next week so we can see what we can do.”The follow-up arrives quickly. Sales is overloaded. Everyone is busy serving customers. Nobody has time for a workshop, but they do have Sales.xlsx. That is what you get. The clock is ticking.And then you open Sales.xlsx.You have nothing. No requirements, no workflows, not even a proper data model. What you have is a snapshot of the messy reality Sales is dealing with every day. Customer names, contacts, opportunity values, dates, products, notes, colors that apparently mean something, and a field called Status_Final_2, which tells you enough about its history that asking about Status_Final_1 would probably ruin the afternoon.And then it strikes you: they are not even using the CRM. You do not know why. Nothing you know from IT seems to apply in Sales, and they do not particularly care. They have customers to serve. Whatever happened between the shiny CRM rollout and this spreadsheet happened years ago. Today, Sales.xlsx is the truth.And now, just because AI promises productivity, they are asking for the benefits.How is that even supposed to work?

Behind every breakthrough in Generative AI isn't magic—it's mathematics."​Ever wondered what actually happens inside a Large Language Model when it generates the next token? Beyond the hype and high-level API calls lies an elegant foundation of probability, vector geometry, and linear algebra.​In The Mathematics of Generative AI, Ahmed Adawy strips away the academic jargon to reveal the exact core equations driving modern LLMs. From conditional probability and high-dimensional embeddings to Query-Key-Value attention mechanisms, this capsule equips software engineers and AI practitioners with the intuition needed to build, debug, and innovate with confidence.​Stop treating AI like a black box. Master the equations beneath the intelligence.

Os agentes de programação com IA avançam rápido. O fluxo de trabalho do Git, baseado em staging e commits, nem sempre consegue acompanhar esse ritmo.Juju-chu! mostra como usar o Jujutsu🐦‍⬛ para registrar commits automaticamente, desfazer operações com confiança e reorganizar com mais segurança as alterações difíceis de organizar que a IA gera. Tudo isso mantendo a compatibilidade com o Git e o GitHub. Para desenvolvedores que já usam o Git e querem um fluxo de trabalho com IA mais tranquilo.

AI can sound certain even when it is completely wrong. This book takes a practical approach to building RAG systems and AI agents that ground answers in evidence, verify what they generate and know when to stop. Learn how to make AI more reliable in the places where getting it wrong really matters.

Build AI agents that reason when necessary, preserve what they learn, and stop paying the intelligence premium for work they already know how to perform. Smart AI Agents combines architecture, working implementations, public source code, and measured experiments to show how agents can learn once and execute many.

Los agentes de programación con IA pueden avanzar más rápido de lo que permite el flujo de trabajo de Git basado en staging y commits.Juju-chu! muestra cómo Jujutsu🐦‍⬛ te da commits automáticos, una forma confiable de deshacer operaciones y una manera más segura de reorganizar los cambios desordenados que genera la IA, todo con compatibilidad total con Git y GitHub. Para desarrolladores que ya usan Git y quieren un flujo de trabajo con IA más tranquilo.

AI agents are moving from experiments into real production systems. This book shows experienced engineers how to design, deploy and operate reliable agent systems that can scale. From architecture and infrastructure to security, reliability and governance, it provides practical patterns and production-ready examples for building autonomous systems that work in the real world.

Unlock the full potential of Claude Fable 5.1 with practical prompting techniques built for real-world work. Learn how to get better results from coding, research and complex workflows, avoid common mistakes and build reliable AI systems with proven strategies and ready-to-use prompts.

What if your browser could run AI without sending your data to a server? AI in the Browser shows you how to build fast, private and fully local AI applications using WebGPU, WebAssembly and on-device LLMs. From GPU compute to a complete local chat interface, you’ll build everything yourself with practical code.

What if AI could help you find flaws in software logic before they become costly bugs? This practical guide shows you how to use Claude Code alongside proven verification tools to test assumptions, uncover hidden issues and build confidence in your code. From first principles to production workflows, learn a smarter way to verify software with AI.