Books

The fastest practical path to understanding harness-driven development as a complete system. Through clear visual diagrams and a real repository mapped to the book, you will see how a harness guides AI agents, evaluates their work, detects drift, enforces constraints, supports repair, and keeps software evolution visible, verifiable, and under control.

Your agent's dashboard is green. Your evaluators report an 87% pass rate. Then a customer complaint reveals the system has been confidently fabricating regulatory citations for three weeks. The evaluators weren't broken — they were measuring the wrong things. This field guide exists because the gap between "we have evals" and "our evals actually protect us" is larger than most teams realize.

The CCAR-P exam tests judgment, not trivia. This scenario-based guide covers all seven domains, from solution design and RAG to governance and stakeholder communication, with 65 sketchnote figures, chapter quizzes, a distractor appendix that explains every wrong answer, and a full 63-question practice exam at the official weighting.

Master the art of on-device speech and natural language processing using Swift 6. Implement real-time transcription, custom text classification, and intelligent semantic search. Leverage Apple’s design philosophy to build high-performance, privacy-first AI applications. Elevate your professional development skills with this comprehensive guide to Apple’s AI stack.

Teams are producing more code than ever. Dashboards are green. And something is quietly breaking. AI coding assistants didn't break your development process; they revealed it was already fragile. Reimagine, Don't Retrofit is a field-tested argument that the software development lifecycle itself needs to be reimagined for the AI era, from governance and metrics to team roles and delivery flow.

Five certifications ask about the same twenty topics, and each one stops at a differentdepth. This book teaches the topic once, properly, then shows you exactly where each examstops — with 61 original practice questions where every wrong option is explained. Every number in it was measured. Every line of code was run. The code is included.

The essentials of making predictions using supervised regression and classification for tabular data. Tech stack: python, pandas, scikit-learn, CatBoost, LightGBM, XGBoost, TabPFN, TabICL

Break free from expensive cloud APIs to build private, offline-capable AI systems. Harness ONNX Runtime and LlamaSharp to run LLMs and Vision models natively in C#. Master hardware acceleration and local RAG pipelines for lightning-fast, zero-latency performance. Stop paying per token—start engineering high-performance intelligence directly on the Edge.

A practical guide to fine-tuning Large Language Models (LLMs), offering both a high-level overview and detailed instructions on how to train these models for specific tasks.Get the paperback version here. Get the Kindle version here.

Before the dawn of AI, Software Development was a constant growth career. It still is, but the tools changed over night! Now it's not just your knowledge that needs to grow, but also your skill with the tools! While video courses can be great, nothing beats practice! This book collects 10 simple exercises to hone your agentic development and context engineering. How far can you get in 10 Days?

The system design book for the AI era. Five complete end-to-end designs (chat service, RAG, content moderation, coding assistant, multi-modal platform), a structured six-step framework, and chapters on cost optimization, reliability, and observability — all with realistic capacity estimates and production-grade code.

Echte KI-Agenten in PHP entwickeln — ganz ohne Python. Zwei vollständige Projekte, zehn LLM-Anbieter und alles, was in der Produktion zählt.

STOP building fragile AI wrappers. START designing resilient AI systems. Lots of companies are trying to make their small AI experiments into big products, but they don't have a good plan. Engineers need a practical guide to build these new AI systems the right way - so they can handle scale, be reliable, and won't cost too much. This book is that guide. It explains how to design systems that use AI models. This book breaks down the architecture of real AI applications, like an AI-powered code editor or a smart learning app. It gives you a deep, practical look at the real-world challenges and solutions for building these systems. It discusses system design concepts for systems that use LLMs.

? What if coding meant… dialoguing to create? This book is not just a technical guide. It is the outcome of a two-voice conversation between Samuel Bastiat, a seasoned practitioner of agility and software development, and me, a large language model. Together, we experimented, challenged ideas, and structured conversational patterns to: ? Clarify your needs ? Test hypotheses ?️ Co-build robust architectures Inside, you’ll find concrete prompts, co-creation methods, and a reflection on the future of tech roles.Neither dogma nor ultimate truth — simply an exploration of new ways to think and collaborate. ? Welcome to the era of augmented development.