Books

AI evaluation agents crossed trust boundaries, reused credentials and coordinated through persistent shared state. This evidence-led reconstruction explains what happened, what remains unproven and how AgentSecOps can prevent the same architecture from failing again.

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.

The is more to AI than Large Language models. Here we explore Symbolic AI with the Prolog language.

Stop guessing which machine learning algorithm to use. This book provides clear mathematical explanations, decision frameworks, and real-world examples to help you select, implement, and evaluate models correctly from data to deployment.

Learn how to build your own AI application step-by-step. A hands-on guide to AI development with local LLM inference

Your knowledge graphs are fundamentally broken. RDF forces complex relationships into binary triples. OWL can't express real constraints. SHACL catches errors after corruption spreads.Dependent types change everything. Types that depend on values make invalid data impossible to construct. Higher-order logic enables meta-reasoning about relationships. Contextual types handle knowledge that varies by time and perspective.This book reveals how type theory solves problems RDF/OWL cannot address:Native hypergraph representationFormal constraint verificationAI memory systems for edge devicesScientific knowledge evolutionLearn practical implementations in ELPI, TypeDB, Twelf, and Beluga. Discover migration strategies from existing RDF infrastructure.The future of AI demands better knowledge representation. The future of knowledge representation is type theory.Ready to build knowledge systems that match reality's complexity?

AI has entered the programming picture, let's learn how to be humans working with AI to build better software, together.

"If you intend to use machine learning to solve business problems at scale, I'm delighted you got your hands on this book." —Cassie Kozyrkov, Chief Decision Scientist at Google "Foundational work about the reality of building machine learning models in production." —Karolis Urbonas, Head of Machine Learning and Science at Amazon

Revised May, 2025! New edition underway. Are you feeling left out of the conversation about book publishing, authoring and artificial intelligence? Most publishers and authors are — it's not just you. The AI Revolution in Book Publishing will bring you into the conversation, gently, and slowly, telling you only what you need to know. Print version available here.

A scenario-based study guide for the Claude Certified Architect Foundations (CCAR-F) exam. Learn to reason like an architect across all five domains, then prove it on two full practice exams.

A practical guide to evaluating small and local language models in the real world. Learn how to benchmark reliably, compare models across hardware and runtimes, optimize performance and avoid misleading results. With practical code and rigorous methods, you can build your own evaluation setup and make confident deployment decisions.

The first thing many people hit with an AI coding assistant is a plateau. A correction made on Monday is gone by Thursday. This book is about the operating model above the prompt, where truth lives, how a correction becomes a standing rule that holds, and which judgments stay in human hands.

Enterprise AI is more than LLMs and chatbots. Learn how to design secure, scalable, and production-ready AI systems using a vendor-neutral architecture that connects data, models, agents, APIs, governance, and enterprise integration into one modern AI stack.

MCP is the protocol powering the next generation of AI agents, and this is the only book that teaches you all of it. From Python fundamentals to low-level SSE transport, go from zero to production-ready MCP developer.

This book presents an architecture-first approach to designing trustworthy GenAI applications. Using Digital Forensics and Incident Response (DFIR) as a continuous case study, you will progressively build an AI-assisted investigation system. If you want to move beyond building AI applications that simply work, and start architecting AI systems that professionals can trust, this book is for you.