Agentic Engineering

AI agents don’t fail because they forget everything. They fail because they remember badly. This book shows you how to engineer memory that stays accurate, efficient and useful over time. From SQLite and PostgreSQL to vector indexes and multi-agent systems, you’ll learn what it takes to build agents that can run for days without losing the plot.

Turn a small language model into an AI agent that runs on your own hardware. This practical guide takes you from choosing a base model to fine-tuning, tool use, evaluation and deployment. With reproducible code and real configurations throughout, you'll learn how to build specialized local agents that are capable, efficient and truly yours.

AI agents are only as good as the loops behind them. This book shows you how to build systems that plan, act, evaluate and improve with every step. Learn the patterns, frameworks and engineering practices behind reliable, self-correcting agents that solve real problems in production.

Unlock the full potential of Moonshot AI's groundbreaking Kimi K3 with practical prompting techniques, real-world examples and production-ready strategies. Whether you are building AI applications, conducting research or deploying autonomous agents, this guide helps you get better results from one of the world's most capable open models.

Build intelligent AI applications with LangChain using practical, production-ready Python examples. From intelligent agents and retrieval-augmented generation to scalable deployment and observability, this book equips you with the skills and architectural understanding needed to create reliable, real-world LLM-powered systems.

Build AI agents that do more than generate text. This book shows you how to use the Claude Agent SDK to create autonomous systems that use tools, manage context, coordinate multiple agents, and solve complex tasks. With practical examples in Python and TypeScript, you will learn how to build secure, scalable agents ready for production.

Local Intelligence shows you how to run large language models entirely on your Mac with Apple Silicon. Learn to use tools like Ollama, MLX, and llama.cpp, understand quantization, and build real local AI applications with open-source code.

Learn how to build, run, and optimize llama.cpp from the ground up. This book covers everything from compiling the code and working with GGUF models to deploying fast, production-ready local LLM inference.

Learn how modern LLM inference engines work by building one from scratch in Rust. From transformers and tokenization to KV caching, quantization, batching, and GPU optimization, this book combines theory, hands-on code, and performance engineering to help you create fast, production-ready AI systems.

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.

A two-part study guide written against the Claude Certified Architect blueprints, Foundations (CCAR-F) and Professional (CCAR-P). Organised domain-by-domain and weighted to match each exam, it teaches the architectural judgement and anti-pattern recognition the exams reward, not a feature tour, across Claude Code, the Agent SDK, the Claude API, and MCP.

Transform static maps into intelligent systems with Geospatial AI (GeoAI) with Python Programming. Bridge the gap between GIS and AI, from satellite image analysis to autonomous LangChain agents. Master production-ready code for GNNs, U-Net architectures, and real-time spatial dashboards. Stop just looking at the map—teach your code to understand it.

Stop building chatbots and start architecting autonomous digital workers that act, plan, and collaborate. Master multi-agent orchestration with CrewAI and build self-healing, cyclic workflows using LangGraph. Move beyond simple prompts to implement the OODA loop, browser automation, and production-grade security. Transform LLMs into reasoning engines capable of managing entire software agencies without intervention.

AI governance changes when AI stops merely producing answers and begins taking action. Runtime AI Governance provides the architecture, controls, evidence and assurance methods practitioners need to govern agentic AI while consequential actions are still observable, interruptible and accountable.