Books

A clear, illustrated guide to large language models, covering key concepts and practical applications. Ideal for projects, interviews, or personal learning.

Language models guess. Knowledge graphs know. Rusty Graph shows you how to build a local AI agent whose memory is a real knowledge graph — typed, validated, reasoned over, and queryable with SPARQL — all inside a single static Rust binary. No JVM. No Docker sidecar. No Python runtime bolted to the side. You will build Ares a research-assistant agent that observes papers, forms beliefs, makes promises to other agents, and tracks the provenance of every fact it holds. Chapter by chapter, Ares grows from an empty Cargo workspace into a full pipeline: > load → reason → validate → query → answer All of it in under a thousand lines of idiomatic Rust, using three crates that actually work today: `oxigraph`, `reasonable`, and `rudof_lib`. `grapfeo` You will learn how to- Model a domain as RDF triples and load them into an embedded store. - Write RDFS and OWL 2 RL axioms that infer trust, identity, and inverse relationships — automatically. - Guard your graph with SHACL shapes that reject bad data at the boundary, not in production. - Query everything with SPARQL, from simple lookups to federated queries across named graphs. - Wire the graph into a hybrid RAG pipeline so your LLM answers are grounded in facts, not vibes. Who it is forRust developers building agents, assistants, or any system where the answer "the model said so" is not good enough. You should be comfortable with Cargo and traits. You do **not** need any prior semantic-web background — every concept is introduced through Ares before any formal definition appears. Why Rust, why nowLocal agents are the next deployment target: a user's laptop, a Raspberry Pi, a WASM sandbox. Python cannot go there comfortably. Rust can. This book is the missing manual for the Rust side of the semantic web — the one that tells you exactly which crates work, where the ecosystem is thin, and how to ship anyway. Stop hoping your model tells the truth. Give it a graph that does.

Master language models through mathematics, illustrations, and code―and build your own from scratch!

Everything you really need to know in Machine Learning in a hundred pages.

A leader at a company opens Slack one morning. The brief their virtual employee wrote looks normal: same headers, same prose voice, same cadence as every other brief that week. The last line ends mid-sentence. The API returned `stop_reason: "max_tokens"`. The system shipped it anyway. No exception. No log line. No retry. That bug doesn't look like the normal kind. This book is about why, and what to build instead.

Securing AI requires a system-level approach across models, data, identities, tools, infrastructure, and execution paths. This book shows how to apply Product Security and Secure SDLC principles to AI-enabled products, from RAG and agents to MCP, evaluations, supply chain risk, runtime controls, and governance, while building the fundamentals needed for a practical AI Product Security operating model.

Your applications lives and runs in more places - MCP, desktop applications, browser-based application, data integration pipelines, gRPC, browsers, etc. - than ever. Can your security framework keep up? If you're using Spring Security, then it definitely can, and this book - by Spring Developer Advocate Josh Long - will show you how.

Ihre Use Cases haben einen neuen Leser: einen KI-Agenten, der sie direkt in Code und Tests umwandelt. Die Implementierung ist mittlerweile kostengünstig, doch die präzise Formulierung der Absicht stellt den Engpass dar. Dieser Leitfaden vermittelt Ihnen, wie Sie Use Cases verfassen, die sowohl für Stakeholder und Ingenieure als auch für die KI-Agenten, die sie umsetzen, funktionieren.

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.

You don’t need massive compute or big-tech resources to build real AI. This hands-on guide shows you how to build and fine-tune your own small language model—from scratch—using accessible tools like Google Colab. Learn transformers step-by-step, train and align models on your own data, and deploy practical AI systems that run on consumer GPUs. If you’ve ever wondered “Can I build my own model?”—this book proves the answer is yes.

Build a complete LLM inference engine in C++ — from a blankproject to a working Transformer that loads a real model andgenerates text. Forged one challenge at a time, with teststhat prove every piece works before you move on.

Skip the black-box frameworks. Build a production-grade AI coding agent from scratch in pure Python - cloud or local, tested with pytest, all in a single file.

Reverse engineering gets a powerful upgrade with Claude Code. Learn how to investigate, understand and reconstruct software you’re authorized to analyze, while keeping evidence, accuracy and reproducibility at the center. From legacy systems to modern codebases, this book turns AI into a practical partner for serious software analysis.

Vector stores don't think — they search. They find fragments that sound like your query, then forget they ever looked. Every session starts from nothing. Every context window is a memory that dissolves at sunset.But the deeper problem isn't amnesia. It's that when agents do remember, they remember in someone else's house — on servers you don't control, in formats you can't inspect, under terms you didn't write.Memory Graph is a book about building something different: persistent, structured, queryable memory that lives inside your application — no external servers, no data leaving your process, no infrastructure you don't own. An embedded graph database that travels with your agent the way a nervous system travels with a body.You'll learn how to model not just facts, but relationships between facts. Causality. Temporal ordering. The layered structure of meaning that makes memory more than a search index. You'll build ontologies that enforce what can be known and how. You'll combine graph traversal with semantic search — so your agents find not just what's similar, but what's connected.The result is an agent that remembers the way you do: structurally, contextually, privately — with memory that belongs to you.

Your use cases have a new reader: an AI agent that turns them directly into code and tests. Implementation is now cheap but expressing intent precisely is the bottleneck. This guide teaches you to write use cases that work for stakeholders, engineers, and the AI agents that implement from them.