Books

This book teaches harness engineering as a discipline. Not magic prompts. Not vendor tricks. Engineering practice applied to a new substrate.

You have been using AI as a faster keyboard.The engineers who will define the next decade are using it as a cognitive workforce they direct, constrain, and govern. The gap between those two practices is not a matter of better prompts. It is a matter of an entirely different mental model.This book is that mental model. Built from first principles. Illustrated through 28 chapters of real architectural decisions, real failures, and real production systems.From execution to orchestration. The complete practitioner guide.

A hands-on guide to building with Claude Code, MCP, the Claude API, and the Agent SDK. From mental models to production architectures — everything an experienced developer needs to work agentically, not just use AI tools.

It's never been easier to build an AI agent — and never been harder to make one that actually works. This book takes you from language model foundations to production-ready multi-agent systems with the depth to predict failure before it happens, engineer graceful degradation over catastrophic failure, and take absolute architectural ownership. Get the paperback from amazon.

This third edition covers Rust 1.85 and the Rust 2024 Edition in full. The new chapters on concurrency, the 2024 edition migration, GPU computing, Go integration, and Linux kernel programming show where the Rust community has moved since the second edition, and where systems programming as a discipline is heading. You might be writing your first Rust function or your hundredth production service, but I hope this book makes the language feel less like a puzzle and more like a tool you are already familiar with. That was the only goal I had when I wrote it.

A fundamental architectural manifesto on AI behavioral safety and the transition from "word generation" to "state synchronization." Stop building "smart calculators"—start building reliable environments.

The universe is no longer just observed; it is computed through the lens of Python and Artificial Intelligence. Master NASA-grade orbital simulations, classify galaxy morphologies with CNNs, and deploy Vision Transformers. Create autonomous LLM agents that mine ArXiv for breakthroughs and GANs that generate realistic nebulae. Join the new breed of scientist-programmers and build the future of computational astronomy today.

Evaluating Gen AI Applications is a practical Safety and Validation Engineering guide for teams that need to make Gen AI systems measurable, observable, secure, and production-ready. It shows how to move beyond ad-hoc prompt testing and build evaluation systems that produce evidence: test results, traces, rubrics, release gates, human-review records, red-team findings, and audit-ready governance artefacts.

A practical playbook for the Forward Deployed Engineer responsible for shipping enterprise AI beyond the demo. Learn how to work across data, RAG, agents, integration, evaluation, observability, governance, cost, security, stakeholders, and handover to make AI systems survive production.

Master AI integration on Apple platforms by bridging Swift 6 with OpenAI, LangChain, and autonomous agents. Build high-performance RAG pipelines using hardware-accelerated vector math and persistent local semantic memory. Architect thread-safe, real-time apps with strict concurrency, intelligent function calling, and efficient token streaming. Move from basic API calls to production-grade intelligence with the definitive guide for modern Apple developers.

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.

Build MCP servers from scratch — from protocol to production deployment. Learn Tools, Resources, Prompts, HTTP transport, authentication, testing, and server composition. 14 chapters, one real project, complete TypeScript code.

Build a complete AI agent from scratch — from a simple API call to a production multi-agent system with memory, planning, RAG, security, and deployment. 15 chapters, one real project, complete Python code.

Rewiring Software Delivery shows technology leaders how to move beyond AI tool adoption and redesign the operating model for agentic engineering. It introduces practical ways to govern autonomous execution, strengthen intent, separate generation from validation, and build a delivery system that turns AI activity into durable business advantage.