Harness Engineering

Give AI agents durable rules, skills, and workflows for solo game development.

vLLM and SGLang, side by side. Learn how LLM serving works, measure both engines fairly, tune them with evidence, and take a model from an empty GPU to a deployment with a cost per million tokens you can defend.

Building AI agents is one thing. Making them reliable in production is another. This book explores why agents fail and how to design systems that hold up under real-world conditions. From architecture and engineering patterns to evaluation and operations, it gives technical leaders the tools to build agents they can trust.

Your AI coding agent starts every session knowing nothing about your project, so it guesses - and the guess is sometimes expensive. The AGENTS.md Cookbook shows you how to write short, specific rules files, how to test them with a simple before-and-after method, and includes twelve ready-to-adapt recipes for real project types, labeled honestly about what has and has not been tested.

Build agents that write code, fix tests, and commit changes while you sleep — safely, cheaply, and entirely on your own hardware (622 manuscript pages).

Meta Muse changes the way you work with AI. This practical guide shows you how to write better prompts, build reliable workflows, automate everyday tasks and avoid common mistakes. Whether you're new to agentic AI or already putting it to work, you'll learn how to get more done with less friction and more confidence.

Enterprise AI becomes dangerous when generated claims, retrieved evidence, human decisions, and autonomous actions are treated as equally trustworthy data. Accountable Knowledge Architecture for Enterprise AI presents an edge-native architecture for building distributed knowledge systems where every claim can be traced to its evidence, authority, decisions, and outcomes giving humans, models, and autonomous agents knowledge they can use without sacrificing accountability.

Get more from Gemini 4 Argon with practical prompting techniques that work on real-world tasks. This guide covers coding, research, legal and financial work, long-horizon workflows, optimization and prompt evaluation, with clear examples and strategies for getting reliable results from one of the most capable AI models available.

Build Smarter Chatbots and Voice AssistantsExplore Conversational AI from fundamentals to real-world applications. Learn NLP, intent and context management, intelligent chatbots, voice assistants, speech technologies, multimodal interfaces, APIs, deployment, business integration, analytics, ethics, LLMs, and Generative AI.

Go beyond basic prompting and learn how to get reliable, high-quality results from Claude Opus 5.5. This practical guide shows you how to structure instructions, manage context, break down complex work and verify outputs across coding, research, analysis, writing and automation.

GPT-6 Astra changes the way prompting works. This practical guide explains what makes it different, why old techniques can fail and how to write prompts that deliver reliable results. Learn how to build, refine and troubleshoot prompts while finding the right balance between control and autonomy.

Build AI agents that actually hold up in production. This practical guide covers agent architecture, tool use, multi-agent systems, security, reliability, observability and operations, with working code throughout. Learn how to build agents that are dependable, cost-aware and ready for the real world.

AI agents are moving from experiments into real production systems. This book shows experienced engineers how to design, deploy and operate reliable agent systems that can scale. From architecture and infrastructure to security, reliability and governance, it provides practical patterns and production-ready examples for building autonomous systems that work in the real world.

A vendor-neutral, mechanism-level field guide to operating and extending agentic coding harnesses (542 manuscript pages).

What if your browser could run AI without sending your data to a server? AI in the Browser shows you how to build fast, private and fully local AI applications using WebGPU, WebAssembly and on-device LLMs. From GPU compute to a complete local chat interface, you’ll build everything yourself with practical code.