Artificial Intelligence

Build AI agents that go beyond conversation._ AI Agents Mastery_ is a practical guide to designing, building, deploying, and scaling autonomous AI agents for real-world applications.Learn how to combine LLMs with tools, APIs, workflows, memory, state, retrieval, automation, security, monitoring, and human oversight to create capable and reliable AI agent systems.From the fundamentals of agent architecture to production deployment and responsible autonomy, this book provides an end-to-end framework for turning AI-agent ideas into practical applications.Learn the principles. Build the systems. Deploy with confidence.

Most vector search books start with the database. This one starts with the machine. Build a search engine from scratch, then push it from brute force to billion-scale retrieval with SIMD, HNSW, quantization and distributed systems. By the end, vector search won't be a black box. It'll be something you know how to build, tune and scale.

The practitioner's guide to policy-space response oracles: one 84-line loop, one readable repository, and every claim backed by a committed experiment — including the ones that came out wrong.

Stop copying code snippets into chat widgets. Master closed-loop autonomous AI coding agents, local offline LLMs (Ollama/Llama 3.1), event-driven lifecycle hooks, and Model Context Protocol (MCP) runtimes.

Explore the foundations and future of modern computing—from artificial intelligence and distributed systems to cybersecurity, quantum technologies, and responsible computing. Modern Computer Science connects essential concepts with emerging technologies, real-world applications, and the challenges shaping the future of the discipline.

Master LTX 2.5 from the first prompt to the final shot. Learn to create cinematic video with synchronized audio, precise camera movement and consistent characters while avoiding the mistakes that waste time and generations. Built on official documentation and verified behavior, this is a practical guide to getting production-ready results from LTX 2.5.

Use LoRA because it forgets less. Keep the learning rate low. Mix in some general data. Stopearly. Four pieces of advice everyone repeats and almost nobody quantifies. This book measures each one — and two turn out to be doing something other than what they arecredited with. LoRA's retention is governed by a scaling constant, not by its parameterefficiency. Early stopping bounds the damage without separating it from the gain. Everyexperiment reports two numbers: the new task, and the capability you were not trying tochange.

The model is only half the system. Learn to design the scaffolding, tools, sandboxes, verification loops, and memory that turn raw LLMs into reliable, production-grade AI agents that actually finish the job.