Large language models

Software development is changing fast, and Claude Code is at the center of that shift. Learn how to work effectively with AI agents to write code, automate workflows, and build larger projects with confidence. From setup and prompt design to real-world engineering practices, this book provides a practical guide to modern software development in 2026.

Code Is the Side Effect"Software engineers are not primarily code writers. We are clarity traders — and that hasn't changed."You've seen the demos. The AI builds a whole feature from a sentence. The agent writes tests, fixes the failing ones, opens the PR. It's remarkable.Then you come back three months later. The codebase is a tangle. Nobody knows why anything is the way it is. The agent that built it has no memory of what it decided or why. And every time you ask it to add something new, it breaks two things you didn't know were connected.This is the pattern that nobody talks about. AI coding tools make the easy parts of engineering dramatically easier. They leave the hard parts untouched — and they create new hard parts that didn't exist before.Ways of Working is the book for engineers who want to work with AI agents rather than be gradually replaced by them — who understand that the tools are genuinely powerful and genuinely limited, and want to build practices that get the most from each.What you will actually learnThe world model framework. Before an agent can build anything well, it needs to understand what it's building and why. This book teaches you to give agents what they need: a structured, queryable representation of your architecture, your component contracts, your behavior specifications, and your code patterns. No world model = no sustained agentic development.Intent documentation. The most expensive bug in agentic codebases is not a hallucination — it's a decision made without context. Why is this rule here? Why is this boundary where it is? Agents can't infer rationale from code. You have to write it down.Spec-Kit and formal specifications. GitHub's Spec-Kit brings machine-readable, traceable, CI-verified specifications to engineering teams. This book shows how to use it to turn requirements into agent inputs that are precise enough to generate correct implementations.Graph explainers. Tools like Graphify and Understand-Anything transform codebases and documents into queryable knowledge graphs — giving agents navigable context instead of flat text. This is the memory substrate that makes multi-agent systems reliable at scale.Agent architecture that holds. What makes an agent coherently itself? When do file-based agent systems break down and what replaces them? How does constraint-based coordination (borrowed from holocracy) solve the autonomy-coherence problem that has stumped AI researchers for decades?Claude Code, for real. A complete treatment of Claude Code's CLAUDE.md convention, permission model, hooks, and slash commands. Plus the oh-my-claudecode ecosystem: 15+ specialized agents, workflow orchestration patterns (autopilot, ralph, ultrawork), and the skills framework for team-specific automation.The AI-native organization. What genuine AI-native teams look like beneath the marketing. How to hire, structure, and lead them. What language-oriented programming and constrained natural language mean for the future of the human-code relationship.Who it's forEngineers who are past the "should I use AI?" question and into the "how do I use it without losing my engineering integrity?" question.Senior engineers. Engineering managers. Technical leaders. People who have noticed that the more they delegate to AI, the less certain they feel — and who want to understand why.From the AuthorI've been building production systems with AI agents for years. Not demos — systems that had to work reliably across months, maintain themselves as requirements changed, and produce outputs that engineers could understand and defend.That experience has made me skeptical in both directions.Skeptical of the "AI will do everything" vision — because I've watched too many AI-generated codebases collapse under the weight of accumulated misunderstanding.Equally skeptical of the "nothing fundamentally changed" position — because the engineers who treat AI coding tools as just faster autocomplete are making a category error they'll pay for in months of maintenance debt.Something genuinely new is happening. This book is my attempt to think about it clearly.

The latest version of Rust (1.85) has some great new features, like async closures, more stable associated function return types, and const generics that are now mature enough to underpin serious numerical libraries. The linfa and smartcore ecosystems have developed into decent classical machine learning stacks. The Burn training framework feels native to Rust, not like it's been ported from it. The Candle makes it so that loading pre-trained transformer models is more of an engineering task than a research exercise. The crates that used to need all sorts of workarounds now just work.

A hands-on guide to downloading, running, serving, and maintaining open-weight LLMs on your own machine (492 manuscript pages).

Bestselling book on building LLMs. A practical, project-driven manual for engineers who want to understand how modern language models are built — and where they fail — by writing every layer themselves. From a scalar autograd engine to RLHF to fused specialists, in 36 hands-on projects with deliberate sabotage experiments. Build it. Break it. Measure it.

Learn how to build reliable AI agents with PydanticAI, from simple chatbots to production-ready multi-agent systems. With practical examples, clear explanations, and hands-on projects, this book helps you write AI applications that are structured, testable, and easy to maintain.

Build AI agents that do more than generate text. This book shows you how to use the Claude Agent SDK to create autonomous systems that use tools, manage context, coordinate multiple agents, and solve complex tasks. With practical examples in Python and TypeScript, you will learn how to build secure, scalable agents ready for production.

Learn how large language models work instead of relying on black-box APIs. Building Large Language Models from Scratch takes you through training a Transformer model in PyTorch, from raw text to a working inference API, covering tokenization, attention, distributed training, and alignment along the way.

Building fast LLM inference is about far more than turning the right knobs. This book takes you inside vLLM and the systems behind it, showing how memory, scheduling, GPUs and distributed serving shape real-world performance. Learn how to measure what matters, find bottlenecks and build inference infrastructure that scales without wasting money.

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

Die Softwareentwicklung wandelt sich rasant, und Claude Code steht im Zentrum dieses Wandels. „Mastering Claude Code“ zeigt, wie Entwickler mit KI-Agenten Code schreiben, Arbeitsabläufe automatisieren und auch komplexe Projekte effizient umsetzen. Praxisnah vermittelt das Buch Einrichtung, Prompt-Design und bewährte Engineering-Praktiken für moderne Softwareentwicklung im Jahr 2026.

Every intelligent system faces a fundamental challenge:How do you find the best solution when there are millions—or even trillions—of possibilities?From A* search and heuristic optimization to neural architecture search, hyperparameter tuning, constraint satisfaction, and quantum optimization, modern AI depends on sophisticated strategies for navigating combinatorial search spaces.In this advanced second volume, Anshuman Mishra explores the powerful algorithms that enable intelligent systems to search smarter, optimize faster, and scale beyond brute force computation.Discover how combinatorial thinking drives machine learning, optimization, quantum AI, and the future of intelligent decision-making.The future of AI belongs to those who understand combinatorial complexity.

Artificial Intelligence is not merely about data, learning, or neural networks—it is fundamentally about exploring vast spaces of possibilities.Every search algorithm, planning system, optimization framework, recommendation engine, and machine learning model faces a common challenge: navigating an enormous combinatorial universe of potential solutions.In Combinatorial Thinking in Artificial Intelligence, Anshuman Mishra reveals the mathematical foundations that drive modern AI systems. Through permutations, combinations, graph theory, probability, search strategies, and optimization techniques, readers learn how intelligent systems reason, search, and make decisions in complex environments.If you want to understand why AI algorithms work—not just how to implement them—this book provides the missing mathematical perspective.Discover the combinatorial engine behind intelligence.

Go beyond prompts and learn how to build AI systems that hold up in production. This book shows how to make context the foundation of reliable LLM applications, covering practical patterns, real trade-offs and proven engineering techniques with clear examples you can put to work right away.