Books

Una guida pratica a Claude Code, scritta con Claude Code.Su Claude Code circolano due tipi di contenuti: video YouTube che si fermano ai primi dieci minuti e thread social che promettono "guide complete" in cambio di un'email. Questo libro nasce dall'esigenza opposta: avere finalmente un manuale che spieghi lo strumento per intero, senza hype e senza muri di lead generation.140 pagine costruite a partire dalla documentazione ufficiale Anthropic, verificate su Claude Code v2.1.123, con esempi reali invece che screenshot da marketing. Si parte dall'installazione su macOS, Linux e Windows, si passa per Plan Mode, CLAUDE.md, gestione del contesto, sicurezza dei permessi, Skill personalizzate, subagent custom, integrazione MCP, e si arriva al prompt engineering aggiornato al 2026 — quello vero, dopo che le formule magiche del 2023 si sono sgonfiate.Il libro è pensato per due lettori in parallelo: lo sviluppatore senior che vuole integrare Claude Code nel proprio workflow di produzione, e chi si avvicina per la prima volta agli strumenti AI agentici e ha bisogno di una mappa. I capitoli iniziali costruiscono le basi senza dare nulla per scontato; quelli avanzati entrano nei meccanismi che fanno la differenza tra un uso superficiale e uno strategico.Tre cose che troverai e che altrove fatico a trovare:Il prompt engineering riletto al 2026. Niente ruoli posticci, niente "agisci come un esperto di...". Le tre leve che contano davvero — istruzioni esplicite, contesto adeguato, esempi curati — applicate al contesto specifico della CLI.Workflow reali, non demo da slide. Esempi concreti su WordPress e Node.js presi da progetti veri, non da repository giocattolo.In apertura c'è una prefazione scritta da Claude Opus, a cui ho dato il manoscritto completo chiedendogli un commento onesto, anche dove il libro non funzionava. È rimasta lì come l'ha scritta: è il modo più trasparente che mi sia venuto in mente per inquadrare il libro.Il libro è gratis — pay-what-you-want con minimo zero. Se ti torna utile e vuoi contribuire, decidi tu quanto. Se non puoi o non vuoi, scarichi e leggi senza pensieri: la licenza Creative Commons BY-SA 4.0 ti permette anche di redistribuirlo e modificarlo, basta citare la fonte e mantenere la stessa licenza.

This book familiarizes readers with the world of LLM and agentic AI, and helps them quickly gain a working-level knowledge of building useful agentic AI solutions for process industry operations. With no prerequisites required, practical demo applications, and a hands-on approach adopted throughout, this book makes advanced AI technologies accessible to process engineers and data scientists alike. It aims to help process data scientists and engineers take their first confident steps into Agentic AI world, understand the full picture, and build a strong enough foundation to keep learning and building on their own. Also available here.

A beginner-friendly introduction to machine learning with Python, that is based on the PyCaret and Streamlit libraries. Readers will delve into the fascinating world of artificial intelligence, by easily training and deploying their ML models!

Aprende los conceptos básicos del Machine Learning y avanza poco a poco con teoría y divertidos ejercicios prácticos en Python a niveles intermedios y avanzados hasta llegar al Deep Learning.Tu camino para convertirte en un Científico de Datos comienza aquí

Dive into NLP, deep learning, knowledge representation, and semantic web technologies. All of my Leanpub books, including this book, can be read for FREE on my web site: https://markwatson.com/

Installing safety hooks for Claude Code takes about thirty seconds. Proving they actually refuse anything is the step almost everyone skips — and an unverified guard looks exactly like a working one. Free: the pre-flight checklist, which event can refuse a tool call and which only watches, how to make a guard fire on purpose, what a broken hook does, and a catalogue of all 915 example hooks in cc-safe-setup.

Accountability cannot be delegated. Execution can. AI can act at a speed and scale that no person can review one decision at a time. The answer is not ceremonial human oversight. It is to establish who owns the workflow, what authority the system has, which limits are enforced and who can intervene when something goes wrong.Human Accountable for the Loop is a practical framework for doing that.

Software changed its front door: we don't open apps anymore; we talk to an assistant. Learn to build for that world —a real AI-native app with MCP, OAuth, and LLMs— using AI as your copilot. From zero to production.

Your tests pass, the agent says it's done — but does your software work? A field manual for verifying what your AI coding agent actually built.

Most agent books teach prompts and frameworks. Agent Engineering teaches the judgment and engineering discipline required to build AI agents that are reliable, secure, testable, and ready for production. Follow a practical Claude-based project from first agent to production-grade autonomous system—and receive every future update to this early-access edition.

Your AI-generated code passes 18,000 tests and reports healthy — while entire data pipelines silently produce nothing. Silent Wiring names the failure mode nobody's tooling catches, and shows you how to find it before your users do.

What happens when AI agents move beyond chatbots and become part of our bodies, ecosystems, cities and even space infrastructure? Explore a collection of futuristic AI concepts through visually rich infographics that imagine the next evolution of intelligent systems.

AI is becoming part of everyday professional work. This practical, non-technical handbook will show you how to use it effectively to save time, improve the quality of your work, make better-informed decisions, and get more done. Learn what AI does well, where human judgement matters, and how to work confidently with AI in the real world.

Your AI prototype works. Now ship it. Most AI frameworks are built for exploration. kdeps is built for production. Define your agent in YAML, declare its dependencies, and deploy it anywhere — Docker, Kubernetes, a standalone binary, an edge device — without rewriting a line when you switch LLM providers. AI Appliances is the hands-on guide to building autonomous AI agents and multi-agent systems with kdeps: deterministic pipelines, real error handling, real deployment, and no vendor lock-in. Write YAML. Run anywhere. Own everything.

You don't need another "intro to LLMs" tutorial. You need patterns—proven architectural blueprints that tell you exactly when to use RAG vs. fine-tuning, how to build agents that don't spiral, and why your retrieval pipeline returns garbage. This book gives you 29 of them, with architecture diagrams and working Python code. Free. No fluff. No vendor lock-in.