Books

> Higher-order logic programming for AI engineers, taught the way *The Little Reasoner* taught recursion. > Your agent's LLM can guess. Can it tell a guess from a fact? > An agent that cannot say "no" cannot be trusted with "yes".

Building multi-agent systems is one thing. Making them reliable in production is another. This book takes you from core architectural concepts to working implementations, covering the patterns, techniques and operational practices needed to coordinate agents, handle failures and build systems that hold up under real-world demands.

Building AI-powered software takes more than plugging into an LLM. This book explores the engineering principles and architectural patterns behind reliable, secure and scalable AI systems. Learn how to move from prototypes to production with practical techniques that stand the test of time, even as models and frameworks evolve.

Breaking into AI engineering takes more than knowing how to code. You need the right skills, practical experience and a clear sense of where the field is heading. Whether you're starting out or looking to move into leadership, this book shows you how to build real-world AI systems, stand out in the job market and grow a career that lasts.

Kod generowany przez AI kompiluje się, przechodzi testy i wygląda na gotowy. Błędy, które się liczą, kryją się w tym, czego brakuje. Praktyczna metoda przeglądu przed wdrożeniem.

Código gerado por IA compila, passa nos testes e parece pronto. Os defeitos que importam estão no que falta. Um método prático para revisar esse código antes do deploy.

Building reliable AI agents takes more than connecting an LLM to a few tools. This book takes you inside the Cursor Agent SDK, showing you how to build, test and deploy agents that hold up in production. Learn the APIs, understand the architecture and turn agentic ideas into systems you can trust.

What if you could make massive Mixture-of-Experts models smaller without retraining them from scratch? This book takes you from the fundamentals of expert pruning to practical implementation, covering proven methods, working code and real-world deployment challenges. Learn how to identify redundant experts, preserve model performance and build pruning solutions that work in production.

Add Gmail search, reading and drafts to an existing OpenAI Agents SDK agent on Windows, with explicitly authorized sending.

Configure Artemis shared memory, documents and local work continuity for an OpenAI Agents SDK agent on Windows.

Install the Artemis HDSM/HDSD gateway on Windows and connect ChatGPT to external memory records and documents.

Persistent memory, hooks, permissions and token cost: what worked when using Claude Code every day in a real small-business operation.

In Place of a PrefaceSometimes a thought arrives before the language to express it. It is already there: you can sense it, circle around it a few times, argue about it, put it to use - and still not quite understand what is happening. Until a thought has a name, it remains almost invisible. Not because it does not exist, but because we keep looking at it through old words.This work began at precisely that point. Not where a complete theory, a rigorous methodology and a settled system of concepts are already in place. Earlier: at the moment when familiar language began to fail, and it became clear that something important was happening, but the old words were no longer enough to name it.So what you have before you is not a conclusion. Not a treatise. Not even a theory in the strict sense of the word.It is a prelude to a hypothesis.The first recorded trace of a question still searching for its own form.That qualification matters. The first account of a new idea cannot be expected to contain everything that must come later: a fully operational definition, an empirical foundation, a classification of cases, a legal framework, an educational protocol and a definitive methodology. All of that will be needed. Perhaps that is exactly what the next step should be. But the first step works differently: it notices rather than proves; it opens rather than closes; it offers no finished map, but draws a first line where there may once have seemed to be nothing.Of course, we are not starting from scratch, nor do we claim that the question itself is wholly new. Long before today, others...