Press quiet lion (12 resultados)

PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

Condición: New. Print on Demand.

Paperback. Condición: new. Paperback. AI applications can be impressive in demos and difficult to understand in production.Traditional monitoring can tell you whether a system is up, slow, or failing. AI applications need more visibility. Teams also need to know what prompt was used, what context was retrieved, which model was called, which tools ran, how many tokens were consumed, what it cost, and how the final answer was produced.AI Observability Explained is a practical guide to making AI systems easier to inspect, debug, operate, and govern once they are running in the real world.Inside, you will learn how to: understand the difference between monitoring, observability, and evaluationdesign traces that explain how an AI answer was producedcapture prompts, retrieval, model calls, tool calls, validation results, and cost signalsinvestigate wrong, slow, expensive, or unsafe AI runsbuild PII-safe logging, redaction, dashboards, alerts, and incident review practicesuse vendor-neutral tracing ideas and production checklists to run AI workflows with more confidenceThe book also uses a small companion lab, ai_observability_lab, to show how these ideas fit together in a simple support-assistant workflow with trace review, validation, tool use, and cost summaries.This book is for software engineers, platform teams, technical leads, security-minded builders, and product teams moving AI systems from experiments into production.If your AI application can generate answers but your team cannot clearly explain why those answers happened, this book will help you build the visibility needed to operate AI systems with more confidence. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

Condición: New. Print on Demand.

PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

Paperback. Condición: new. Paperback. Ancient strategy. Modern software problems. Practical engineering judgment.Software teams rarely face neat textbook problems.They face risky migrations, fragile releases, noisy incidents, unclear ownership, vendor hype, technical debt, security pressure, and roadmaps shaped by both code and humans being human.The 36 Stratagems for Software Teams takes a classic Chinese set of strategic patterns and reimagines them for modern engineering, product, platform, security, and delivery work.This is not a book about manipulation, office politics, or pretending sprint planning is an ancient battlefield. Instead, it uses the Thirty-Six Stratagems as a practical lens for recognizing patterns that software teams already deal with every day: when to move directly and when to move indirectlywhen to wait, contain, simplify, or retreathow to handle migrations without creating unnecessary disruptionhow to use prototypes, feature flags, rollback paths, and stable interfaceshow to recognize hidden risks in tools, vendors, dependencies, and architecturehow to turn incidents, uncertainty, and technical debt into better decisionsEach chapter explains one stratagem in plain language, then connects it to a realistic software-team situation using examples from architecture, platform work, delivery, operations, security, and leadership.You will find practical lessons on: legacy modernizationrelease planningincident responsedependency riskplatform adoptiontechnical debtsecurity controlsteam coordinationproduct and engineering tradeoffsknowing when to stop, rollback, or walk awayPart of The Practical Tech Guide Series, this book is written for engineers, tech leads, engineering managers, product managers, platform teams, security teams, and founders who want a sharper way to think about messy technical decisions. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. AI applications are useful, but they can also become unsafe in subtle ways.A normal application already needs authentication, authorization, input validation, logging, and careful handling of secrets. AI applications add another layer of risk: prompts can be manipulated, retrieved documents can overshare, tools can be exposed too broadly, and generated outputs can look safe while breaking policy.Securing AI Applications is a hands-on guide to building safer AI workflows.Instead of treating AI security as abstract theory, this book follows a small companion project: ai_security_lab, a fictional support-assistant application with support tickets, customer records, policy documents, uploaded content, sensitive tool actions, and audit logs. The project starts with weak boundaries and hardens them step by step.Inside, you will learn how to: recognize prompt injection and untrusted inputtreat retrieved documents as data, not instructionsreduce sensitive data before it reaches the AI workflowdesign safer tool contracts and permission checksadd human approval gates for higher-risk actionsvalidate structured outputs before using them downstreamuse audit logs to make AI actions reviewabletest security controls instead of leaving them as adviceprepare a practical deployment checklist for AI featuresThis book is not about securing a model in isolation. It is about securing the workflow around the model: prompts, retrieval, tools, outputs, approvals, logs, and boundaries.If you are building AI features into real applications, this guide will help you think clearly about what can go wrong - and how to make those risks visible, testable, and easier to control. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. Build practical RAG applications without getting lost in vendor noise.Retrieval-Augmented Generation, or RAG, is one of the most useful patterns for building AI applications that answer from real documents instead of unsupported guesses. But many explanations jump too quickly into tools, vector databases, and frameworks before explaining how the system actually works.This book takes a practical, project-first approach.You will build docs_rag_app, a small local RAG application in Python that answers questions over a folder of documents. Step by step, you will learn how to load documents, split them into chunks, retrieve relevant evidence, generate grounded answers, add citations, evaluate quality, and debug bad results.Along the way, the book explains the ideas behind the code: why LLMs need retrievalhow RAG differs from fine-tuning, long context, memory, and tool callshow chunking affects answer qualityhow lexical and vector retrieval workwhy reranking improves difficult caseshow citations and abstention reduce hallucination riskhow to evaluate and refresh a RAG systemwhy retrieved text should be treated as evidence, not trusted instructionsThe goal is not to build the largest possible AI system. The goal is to build a small RAG application that is easy to inspect, easy to debug, and strong enough to improve.If you can read basic Python and want to understand how retrieval changes AI application design, this guide gives you a clear path from first working prototype to practical local RAG app. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. AI applications can be impressive in demos and difficult to understand in production.Traditional monitoring can tell you whether a system is up, slow, or failing. AI applications need more visibility. Teams also need to know what prompt was used, what context was retrieved, which model was called, which tools ran, how many tokens were consumed, what it cost, and how the final answer was produced.AI Observability Explained is a practical guide to making AI systems easier to inspect, debug, operate, and govern once they are running in the real world.Inside, you will learn how to: understand the difference between monitoring, observability, and evaluationdesign traces that explain how an AI answer was producedcapture prompts, retrieval, model calls, tool calls, validation results, and cost signalsinvestigate wrong, slow, expensive, or unsafe AI runsbuild PII-safe logging, redaction, dashboards, alerts, and incident review practicesuse vendor-neutral tracing ideas and production checklists to run AI workflows with more confidenceThe book also uses a small companion lab, ai_observability_lab, to show how these ideas fit together in a simple support-assistant workflow with trace review, validation, tool use, and cost summaries.This book is for software engineers, platform teams, technical leads, security-minded builders, and product teams moving AI systems from experiments into production.If your AI application can generate answers but your team cannot clearly explain why those answers happened, this book will help you build the visibility needed to operate AI systems with more confidence. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…