Books

Si creés que la IA "democratiza" la programación, este libro te va a discutir: la vara no baja, sube. Estas herramientas son más peligrosas en manos sin criterio. 30 capítulos para dominarlas —incluido cuándo NO usarlas.

Your AI has not forgotten you. It simply cannot show you what it knows, let you correct it, take it with you, or act on it. This book fixes all four: plain files you own, an assistant with hands on them, rules it will not cross, and work that lands before you wake up. No code, no terminal.

El software cambió de puerta de entrada: ya no abrimos apps, le hablamos a un asistente. Aprende a construir para ese mundo —una app AI-native real con MCP, OAuth y LLMs— usando la IA como copiloto. De cero a producción.

The future of AI depends on how we measure it. This book cuts through the hype to show what benchmarks really tell us, where they fall short and why better evaluation leads to better models. Practical, clear and grounded in real-world experience, it is an essential guide for anyone building, studying or deploying modern AI.

A £4.1M PRA compliance failure. A fictional bank called Avon & Wessex. Sixteen chapters and 23 systems showing exactly how to build production-grade, auditable AI for credit, market, operational and liquidity risk, model governance, and regulatory reporting — the practitioner's guide UK banking has been missing.

Discover how to unlock the full potential of Claude Opus 5 with a practical guide built on Anthropic's official documentation and proven best practices. From writing your first effective prompt to designing sophisticated agentic workflows and production-ready systems this book gives you the techniques, patterns and insights needed to achieve more accurate, reliable and consistent results.

An agent can score well on average and still fail exactly where it matters. Beyond “Ship and Pray” shows how to replace benchmark averages with designed experiments, geometric ground truth and failure attribution—so teams can discover when an agent breaks, identify the responsible component and test whether it fails safely under tool faults.

Top-k is not relevance, retrieved text is not evidence and an LLM judging another LLM is not verification. Beyond “Chunk and Pray” shows how to build RAG that answers through a verified knowledge graph, preserves exact numbers, cites its sources and abstains when it cannot prove the answer.

Claude Code puede trabajar solo durante horas. La pregunta no es si confiar en él — es cómo dirigirlo para que ese tiempo no se convierta en el tuyo, limpiando después.

AI made implementation cheap and shared understanding scarce. This is the book about how teams should adapt the process.

FOCUS Architecture presents an opinionated architectural approach for creating simple, organized, and maintainable systems. Instead of multiplying layers and abstractions, the book demonstrates how to structure applications around four components—View, Orchestrator, Use Case, and Repository—thereby reducing the cost of change and simplifying the work for both developers and AI tools.

Two architectures. One choice: process a sequence step by step, or all at once. From that single decision flows almost every difference between RNNs and Transformers: how fast they train, how far they remember, and why parallelism won. A rigorous, diagram-rich comparison that derives the field instead of just surveying it.

Build a complete data pipeline from scratch — no cloud signup needed. Fifteen chapters covering ingestion, loading, data modeling, dbt, Airflow, data quality, streaming, observability, and performance optimization. Everything runs locally with Python and DuckDB.