{"product_id":"a-developers-guide-to-integrating-generative-ai-into-applications-paperback-softback-9781394373130","title":"A Developer's Guide to Integrating Generative AI into Applications (Paperback \/ softback) 9781394373130","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eA Developer's Guide to Integrating Generative AI into Applications\u003c\/font\u003e\u003cbr\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003c\/p\u003e\n\u003cp\u003e\u003cfont size=\"4\"\u003eChris Minnick (Author)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781394373130, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003ePaperback \/ softback, published 16 February 2026\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e416 pages\u003cbr\u003e23.1 x 18.5 x 2 cm, 0.794 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003e\u003cp\u003e\u003cb\u003eCreate, implement, and scale commercially successful generative AI applications that solve real-world problems\u003c\/b\u003e \u003c\/p\u003e\n\u003cp\u003eIn \u003ci\u003eA Developer's Guide to Integrating Generative AI into Applications\u003c\/i\u003e, software developer, technology educator, and author Chris Minnick explain exactly how to design and implement scalable generative AI applications. The book walks you through building production-ready GenAI applications, covering the key architectural choices, integration patterns, and design practices needed to deliver accurate, efficient, and commercially viable solutions. \u003c\/p\u003e\n\u003cp\u003eMinnick demonstrates the principles and techniques you need to succeed in the rapidly evolving GenAI space in real-world business environments. He shows how to overcome the practical challenges developers face when embedding generative AI into products, from designing effective prompts to managing performance and cost, with hands-on examples that demonstrate proven techniques you can apply immediately. \u003c\/p\u003e\n\u003cp\u003eYou’ll discover: \u003c\/p\u003e\n\u003cul\u003e \u003cli\u003eStep-by-step guides to using AI APIs, SDKs, AI-generated data, and synthetic users\u003c\/li\u003e \u003cli\u003eUp-to-date explanations of how to build AI-powered chatbots and assistants, AI-driven content-enhancement services, code generation and software development tools, and AI search and recommendation utilities\u003c\/li\u003e \u003cli\u003eHow to improve your interface and UX design with AI features\u003c\/li\u003e \u003cli\u003eExplorations of business and scaling considerations, including how to monetize AI features, how to optimize AI for both performance and cost, and case studies of successful products that incorporate GenAI\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003ePerfect for software developers, product managers, engineering leaders, and UX designers, \u003ci\u003eA Developer's Guide to Integrating Generative AI into Applications \u003c\/i\u003eis your essential guide to integrating generative AI into real products and creating the AI-powered applications that will define the next era of software.\u003c\/p\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003eIntroduction xxvii\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart I Foundations of Generative AI 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Introduction to Generative AI 3\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eEvolution of AI Applications 4\u003c\/p\u003e \u003cp\u003eKey Eras of AI Development 4\u003c\/p\u003e \u003cp\u003eLogic and Rules-Based Systems 4\u003c\/p\u003e \u003cp\u003eEarly Machine Learning 5\u003c\/p\u003e \u003cp\u003eExpert Systems 5\u003c\/p\u003e \u003cp\u003eBig Data and Statistical Machine Learning 5\u003c\/p\u003e \u003cp\u003eDeep Learning 6\u003c\/p\u003e \u003cp\u003eThe Rise of Generative AI 8\u003c\/p\u003e \u003cp\u003eTransition to GenAI 9\u003c\/p\u003e \u003cp\u003eUnderstanding AI and ml 11\u003c\/p\u003e \u003cp\u003eWhat Machine Learning Can Do 12\u003c\/p\u003e \u003cp\u003eSupervised Learning 12\u003c\/p\u003e \u003cp\u003eUnsupervised Learning 13\u003c\/p\u003e \u003cp\u003eSemi-Supervised Learning 13\u003c\/p\u003e \u003cp\u003eReinforcement Learning 13\u003c\/p\u003e \u003cp\u003eSelf-Supervised Learning 13\u003c\/p\u003e \u003cp\u003eLarge Language Models 14\u003c\/p\u003e \u003cp\u003eTokenization 14\u003c\/p\u003e \u003cp\u003eEmbedding 16\u003c\/p\u003e \u003cp\u003eTransformer Layers 17\u003c\/p\u003e \u003cp\u003ePrediction 18\u003c\/p\u003e \u003cp\u003eWhat Makes Generative AI Different? 18\u003c\/p\u003e \u003cp\u003eGenerating Content 18\u003c\/p\u003e \u003cp\u003eGenAI Is Necessarily Unpredictable 19\u003c\/p\u003e \u003cp\u003eGenAI Is Probabilistic 19\u003c\/p\u003e \u003cp\u003eGenAI Requires Prompt Design 19\u003c\/p\u003e \u003cp\u003eGenAI Is Multimodal 19\u003c\/p\u003e \u003cp\u003eGenAI Shifts UX Expectations 20\u003c\/p\u003e \u003cp\u003eGenAI Needs Guardrails 20\u003c\/p\u003e \u003cp\u003eReal-World Examples of AI Integration 20\u003c\/p\u003e \u003cp\u003eAI-Enhanced Customer Service Bots 20\u003c\/p\u003e \u003cp\u003eGenerative Writing Tools 21\u003c\/p\u003e \u003cp\u003eImage Generation in Creative Tools 22\u003c\/p\u003e \u003cp\u003eSummary 24\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Understanding Generative AI Models 25\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eKey Factors in Choosing a Model 25\u003c\/p\u003e \u003cp\u003eCost and Pricing Structure 26\u003c\/p\u003e \u003cp\u003eLicensing Model 26\u003c\/p\u003e \u003cp\u003ePerformance Metrics 27\u003c\/p\u003e \u003cp\u003eSuitability for Your Use Case 28\u003c\/p\u003e \u003cp\u003eTechnical Features 28\u003c\/p\u003e \u003cp\u003eArchitecture 29\u003c\/p\u003e \u003cp\u003eParameter Count 30\u003c\/p\u003e \u003cp\u003eTraining Objective and Data 30\u003c\/p\u003e \u003cp\u003eFine-Tuning 30\u003c\/p\u003e \u003cp\u003eContext Window 30\u003c\/p\u003e \u003cp\u003eUnique Functionalities 31\u003c\/p\u003e \u003cp\u003eProprietary Models 31\u003c\/p\u003e \u003cp\u003eGPT (OpenAI) 32\u003c\/p\u003e \u003cp\u003eClaude (Anthropic) 33\u003c\/p\u003e \u003cp\u003eDALL·E (OpenAI) 33\u003c\/p\u003e \u003cp\u003eGemini (Google DeepMind) 33\u003c\/p\u003e \u003cp\u003eOpen and Open-Source Models 34\u003c\/p\u003e \u003cp\u003eOLMo (Allen AI) 35\u003c\/p\u003e \u003cp\u003eLlama (Meta) 35\u003c\/p\u003e \u003cp\u003eStable Diffusion (Stability AI) 36\u003c\/p\u003e \u003cp\u003eDeciding Between Proprietary and Open Models 36\u003c\/p\u003e \u003cp\u003eWhen to Use Which Model 38\u003c\/p\u003e \u003cp\u003eAdapting Your Model’s Abilities 39\u003c\/p\u003e \u003cp\u003eFine-Tuning 39\u003c\/p\u003e \u003cp\u003ePrompt Engineering 40\u003c\/p\u003e \u003cp\u003eRetrieval-Augmented Generation 40\u003c\/p\u003e \u003cp\u003eChoosing the Right Adaptation Strategy 42\u003c\/p\u003e \u003cp\u003eWhen to Use Non-Generative Models Alongside GenAI 43\u003c\/p\u003e \u003cp\u003eKey Advantages of Non-Generative Approaches 43\u003c\/p\u003e \u003cp\u003eStrategic Use Cases for Hybrid Approaches 43\u003c\/p\u003e \u003cp\u003eLatency-Critical Applications 44\u003c\/p\u003e \u003cp\u003eCost and Performance Optimization 44\u003c\/p\u003e \u003cp\u003eQuality Control and Validation 44\u003c\/p\u003e \u003cp\u003ePreprocessing and Filtering 45\u003c\/p\u003e \u003cp\u003eDecision-Making and Scoring 45\u003c\/p\u003e \u003cp\u003eWhen to Choose Traditional Approaches Over AI 45\u003c\/p\u003e \u003cp\u003eSummary 46\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Getting Started with AI APIs and SDKs 47\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eExploring Hosted Models 47\u003c\/p\u003e \u003cp\u003eSetting Up a Simple Development Environment 48\u003c\/p\u003e \u003cp\u003eOpenAI Developer Platform 48\u003c\/p\u003e \u003cp\u003eGetting an OpenAI API Key 49\u003c\/p\u003e \u003cp\u003eAnthropic’s Build with Claude 55\u003c\/p\u003e \u003cp\u003eGoogle Gemini Developer API 57\u003c\/p\u003e \u003cp\u003eGenAI Integration Patterns 59\u003c\/p\u003e \u003cp\u003eCommon Architectural Models for Integrating GenAI 59\u003c\/p\u003e \u003cp\u003eBackend Service Integration 59\u003c\/p\u003e \u003cp\u003eFrontend-Only Integration 61\u003c\/p\u003e \u003cp\u003ePlugin-Based Integration 66\u003c\/p\u003e \u003cp\u003eHybrid Integration 66\u003c\/p\u003e \u003cp\u003eModel Access Patterns 66\u003c\/p\u003e \u003cp\u003eSynchronous vs. Asynchronous 67\u003c\/p\u003e \u003cp\u003eStreaming vs. Batch 68\u003c\/p\u003e \u003cp\u003eInput Types for GenAI Integration 69\u003c\/p\u003e \u003cp\u003ePlain Text Prompts 69\u003c\/p\u003e \u003cp\u003eStructured Prompts 69\u003c\/p\u003e \u003cp\u003eMultimodal Prompts 70\u003c\/p\u003e \u003cp\u003eResponse Handling 71\u003c\/p\u003e \u003cp\u003eIntegrating Responses into the User Interface 71\u003c\/p\u003e \u003cp\u003eLogging and Analytics 71\u003c\/p\u003e \u003cp\u003eChaining Responses to Other Services 72\u003c\/p\u003e \u003cp\u003eCombining Techniques 72\u003c\/p\u003e \u003cp\u003eSummary 73\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 AI-Generated Data and Synthetic Users 75\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eGenerating Test Data with GenAI 76\u003c\/p\u003e \u003cp\u003eTraditional Test Data Generation 76\u003c\/p\u003e \u003cp\u003eManual Generation 76\u003c\/p\u003e \u003cp\u003eAutomated Data Generation 76\u003c\/p\u003e \u003cp\u003eData Masking 76\u003c\/p\u003e \u003cp\u003eUsing GenAI for Test Data Generation 77\u003c\/p\u003e \u003cp\u003eIntroducing the Sample App 77\u003c\/p\u003e \u003cp\u003eTechniques for Generating Synthetic Data 79\u003c\/p\u003e \u003cp\u003eFew-Shot Prompting for Schema-Aligned Data 79\u003c\/p\u003e \u003cp\u003eTemplate-Based Generation with Randomized Inputs 81\u003c\/p\u003e \u003cp\u003eStructured Output Formats 83\u003c\/p\u003e \u003cp\u003eSimulating User Behavior and Interaction Flows 86\u003c\/p\u003e \u003cp\u003eSimulating Chat-Based Interactions 86\u003c\/p\u003e \u003cp\u003eSimulating Navigational Flows and Multistep Interactions 87\u003c\/p\u003e \u003cp\u003eSimulating Edge Case and Adversarial Behavior 88\u003c\/p\u003e \u003cp\u003eBest Practices and Limitations of Behavior Simulation 89\u003c\/p\u003e \u003cp\u003eSummary 90\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Prompt Engineering 91\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhy Prompt Design Matters in GenAI Applications 92\u003c\/p\u003e \u003cp\u003ePrompt Quality Affects Output Quality 92\u003c\/p\u003e \u003cp\u003ePrompting Is Cheaper and Faster than Fine-Tuning 93\u003c\/p\u003e \u003cp\u003ePrompts Shape the Voice and Tone of AI 93\u003c\/p\u003e \u003cp\u003eBetter Prompts Reduce Hallucinations 93\u003c\/p\u003e \u003cp\u003ePrompts Embed Business Logic 94\u003c\/p\u003e \u003cp\u003ePrompt Design Supports Edge Case Handling 94\u003c\/p\u003e \u003cp\u003eGood Prompts Improve Performance and Reduce Cost 94\u003c\/p\u003e \u003cp\u003ePrompt Types 95\u003c\/p\u003e \u003cp\u003eZero-Shot Prompting 95\u003c\/p\u003e \u003cp\u003eFew-Shot Prompting 96\u003c\/p\u003e \u003cp\u003eChain-of-Thought Prompting 96\u003c\/p\u003e \u003cp\u003ePrompting Best Practices 97\u003c\/p\u003e \u003cp\u003eGuiding the LLM with System Messages 98\u003c\/p\u003e \u003cp\u003ePrompt Templates for Repeatable Interactions 98\u003c\/p\u003e \u003cp\u003eAdjusting Generation Parameters 101\u003c\/p\u003e \u003cp\u003eMax Tokens 101\u003c\/p\u003e \u003cp\u003eTemperature 102\u003c\/p\u003e \u003cp\u003eTop P 103\u003c\/p\u003e \u003cp\u003eTop K 104\u003c\/p\u003e \u003cp\u003eStop Sequences 104\u003c\/p\u003e \u003cp\u003eDeciding How to Set Inference Parameters 104\u003c\/p\u003e \u003cp\u003eTooling for Prompt Development 105\u003c\/p\u003e \u003cp\u003eIn-Browser Prompt Playgrounds 105\u003c\/p\u003e \u003cp\u003eAnthropic Workbench 105\u003c\/p\u003e \u003cp\u003eOpenAI Playground 112\u003c\/p\u003e \u003cp\u003eGoogle AI Studio 115\u003c\/p\u003e \u003cp\u003ePrompt Management 116\u003c\/p\u003e \u003cp\u003eSummary 117\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart II Designing for a Better AI Experience 119\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Human–AI Interaction and UX Design 121\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eManaging User Expectations 122\u003c\/p\u003e \u003cp\u003eClarify the AI’s Capabilities Up Front 123\u003c\/p\u003e \u003cp\u003eSet Expectations Around Potential Failure 124\u003c\/p\u003e \u003cp\u003eCommunicate When Outputs are Probabilistic 124\u003c\/p\u003e \u003cp\u003eProvide Cues that Suggest When the AI is “Thinking” 124\u003c\/p\u003e \u003cp\u003eUse Progressive Disclosure to Build Trust 125\u003c\/p\u003e \u003cp\u003eAvoid Overpromising AI Abilities 125\u003c\/p\u003e \u003cp\u003eDesigning Interfaces for AI-Powered Features 126\u003c\/p\u003e \u003cp\u003eUnderstand the Users and Context 126\u003c\/p\u003e \u003cp\u003eEnsure Clarity of AI-Generated vs. User-Generated Content 126\u003c\/p\u003e \u003cp\u003eProvide Opportunities for Correcting or Refining AI Outputs 127\u003c\/p\u003e \u003cp\u003eUse Visual or Interaction Cues to Indicate When the AI Is Active or Idle 127\u003c\/p\u003e \u003cp\u003eOffer Undo or Step-Back Controls to Reduce Risk and Build Confidence 127\u003c\/p\u003e \u003cp\u003eDesign for Uncertainty and Failure 128\u003c\/p\u003e \u003cp\u003eBalancing Automation with Human Control 128\u003c\/p\u003e \u003cp\u003eImproving Over Time 129\u003c\/p\u003e \u003cp\u003eCapturing and Using User Feedback 129\u003c\/p\u003e \u003cp\u003eBalancing Explicit Ratings and Behavioral Signals 130\u003c\/p\u003e \u003cp\u003eLearning Without Surprising Users 130\u003c\/p\u003e \u003cp\u003eMonitoring for Drift and Relevance 130\u003c\/p\u003e \u003cp\u003eAccessibility and Inclusion in AI UX 131\u003c\/p\u003e \u003cp\u003eAccessibility Standards for AI Applications 131\u003c\/p\u003e \u003cp\u003eBest Practices for Accessible AI UX 132\u003c\/p\u003e \u003cp\u003eGenAI as an Accessibility Aid 134\u003c\/p\u003e \u003cp\u003eTesting GenAI Accessibility 134\u003c\/p\u003e \u003cp\u003eUsing GenAI to Test GenAI Outputs 137\u003c\/p\u003e \u003cp\u003eHuman-Centered AI in the Real World 138\u003c\/p\u003e \u003cp\u003eSummary 139\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Optimizing AI for Performance and Cost 141\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eFrom Prototype to Production 141\u003c\/p\u003e \u003cp\u003eThe Hidden Cost of GenAI Features 142\u003c\/p\u003e \u003cp\u003eWhy Optimization Matters 142\u003c\/p\u003e \u003cp\u003eThe Trade-Off Triangle 143\u003c\/p\u003e \u003cp\u003eMinimize Latency and Reduce Redundant API Calls 144\u003c\/p\u003e \u003cp\u003eReduce Prompt Size 144\u003c\/p\u003e \u003cp\u003eReduce the Size of the Model’s Response 145\u003c\/p\u003e \u003cp\u003eUse Caching to Avoid Redundant Calls 146\u003c\/p\u003e \u003cp\u003eCache Exact Prompt–Response Pairs 146\u003c\/p\u003e \u003cp\u003ePrompt Fingerprint Caching 148\u003c\/p\u003e \u003cp\u003eReuse Similar Responses with Embedding Search 150\u003c\/p\u003e \u003cp\u003eParallelize Requests 153\u003c\/p\u003e \u003cp\u003eStream Responses 155\u003c\/p\u003e \u003cp\u003ePrecompute for Known Flows 157\u003c\/p\u003e \u003cp\u003eLightweight Fine-Tuning 158\u003c\/p\u003e \u003cp\u003eProfile and Monitor Performance 158\u003c\/p\u003e \u003cp\u003eLogging to Identify Latency Hotspots 159\u003c\/p\u003e \u003cp\u003eObservability Tools for GenAI Systems 159\u003c\/p\u003e \u003cp\u003eHandle Rate Limits Gracefully 160\u003c\/p\u003e \u003cp\u003eUnderstanding Usage Tiers 162\u003c\/p\u003e \u003cp\u003eThrottle and Buffer Requests 162\u003c\/p\u003e \u003cp\u003eDesign for Fallback and Graceful Degradation 162\u003c\/p\u003e \u003cp\u003eSummary 163\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart III Integrating AI into Applications 165\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Building AI-Powered Chatbots and Assistants 167\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eStart with a Simple Chatbot 168\u003c\/p\u003e \u003cp\u003ePrinciples of Conversational Interface Design 174\u003c\/p\u003e \u003cp\u003eManaging Turn-Taking, Flow, and Feedback in Dialogue 175\u003c\/p\u003e \u003cp\u003eShow Feedback and Errors 176\u003c\/p\u003e \u003cp\u003eTemporarily Disable the Input to Prevent Accidental Repeat Submissions 178\u003c\/p\u003e \u003cp\u003eUse Backchannel Cues and Confirmations 178\u003c\/p\u003e \u003cp\u003eGuide the Next Turn 180\u003c\/p\u003e \u003cp\u003eKeep the User Oriented 181\u003c\/p\u003e \u003cp\u003eHandling Memory, Context, and User Personalization 183\u003c\/p\u003e \u003cp\u003eTracking Conversation History 183\u003c\/p\u003e \u003cp\u003eAdding Basic Personalization 186\u003c\/p\u003e \u003cp\u003eSteering AI Toward Specific Tasks or Domains 190\u003c\/p\u003e \u003cp\u003eUsing System Prompts to Constrain Behavior 190\u003c\/p\u003e \u003cp\u003eWelcoming the User 192\u003c\/p\u003e \u003cp\u003eWhen to Use RAG for External Knowledge 194\u003c\/p\u003e \u003cp\u003eAdding Auto-Scroll and Streaming Responses 195\u003c\/p\u003e \u003cp\u003eDesigning for Fallback, Clarification, and Edge Cases 200\u003c\/p\u003e \u003cp\u003eClarify Ambiguous Questions 200\u003c\/p\u003e \u003cp\u003eFall Back When the Answer Isn’t Known 202\u003c\/p\u003e \u003cp\u003eHandle Out-of-Scope Requests Gracefully 202\u003c\/p\u003e \u003cp\u003eBest Practices for Customer Service Chatbots 203\u003c\/p\u003e \u003cp\u003eSummary 204\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Generating and Enhancing Content with AI 205\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBuilding SPOT: Fast, On-Brand, and Grounded 205\u003c\/p\u003e \u003cp\u003eOverview of SPOT 206\u003c\/p\u003e \u003cp\u003eGetting Set Up 208\u003c\/p\u003e \u003cp\u003eWhere to Put This in a Real Application 208\u003c\/p\u003e \u003cp\u003eAI-Assisted Writing and Summarization 209\u003c\/p\u003e \u003cp\u003eGoing from Brief to Draft 209\u003c\/p\u003e \u003cp\u003eRewriting for Tone, Audience, and Locale 211\u003c\/p\u003e \u003cp\u003eSummarization with Source Citations 212\u003c\/p\u003e \u003cp\u003eRepurposing Long-Form Content 212\u003c\/p\u003e \u003cp\u003eChoosing the Right Summarization Mode 213\u003c\/p\u003e \u003cp\u003eKeep It On-Brand with the Style Pack 214\u003c\/p\u003e \u003cp\u003ePrompt-Time Injection 214\u003c\/p\u003e \u003cp\u003ePost-Generation Validation 215\u003c\/p\u003e \u003cp\u003eImplementation Patterns for Your Own Apps 218\u003c\/p\u003e \u003cp\u003eGrounded Writing with RAG 218\u003c\/p\u003e \u003cp\u003eStructured Outputs for Pipelines 220\u003c\/p\u003e \u003cp\u003eEvaluation and Human Review 220\u003c\/p\u003e \u003cp\u003eAccessibility and Inclusive Language 221\u003c\/p\u003e \u003cp\u003eLegal, IP, and Disclosure Considerations 223\u003c\/p\u003e \u003cp\u003eAI-Generated Images and Media 224\u003c\/p\u003e \u003cp\u003eDesign First, Pixels Second 224\u003c\/p\u003e \u003cp\u003eMaintain Brand Consistency in Visuals 225\u003c\/p\u003e \u003cp\u003eImage Editing Workflows 226\u003c\/p\u003e \u003cp\u003eAudio and Voice Features 226\u003c\/p\u003e \u003cp\u003eVideo Workflows: Storyboard First, Shots Second 227\u003c\/p\u003e \u003cp\u003eMeasure What Matters 228\u003c\/p\u003e \u003cp\u003eLogging and Provenance for Media 228\u003c\/p\u003e \u003cp\u003ePersonalization and Dynamic Content 229\u003c\/p\u003e \u003cp\u003eUnderstanding the Personalization Spectrum 229\u003c\/p\u003e \u003cp\u003eDefining Your Signals and Features 230\u003c\/p\u003e \u003cp\u003eRuntime vs. Precomputed Variants 230\u003c\/p\u003e \u003cp\u003eAdding Guardrails for Fairness and Safety 231\u003c\/p\u003e \u003cp\u003eExperimenting and Optimizing 231\u003c\/p\u003e \u003cp\u003eLocalizing and Adapting Across Cultures 231\u003c\/p\u003e \u003cp\u003eLocale-Specific Spelling and Grammar 232\u003c\/p\u003e \u003cp\u003eMultilingual Prompt Templates 232\u003c\/p\u003e \u003cp\u003eCultural Norms and Communication Style 233\u003c\/p\u003e \u003cp\u003eRegional Imagery and References 233\u003c\/p\u003e \u003cp\u003eShowing Your Work: UX Patterns for Trust 234\u003c\/p\u003e \u003cp\u003eCommon Pitfalls and How to Avoid Them 235\u003c\/p\u003e \u003cp\u003eFabrication Masquerading as Authority 235\u003c\/p\u003e \u003cp\u003eBrand Drift 236\u003c\/p\u003e \u003cp\u003eOver-Personalization 236\u003c\/p\u003e \u003cp\u003eHidden Costs and Latency Surprises 237\u003c\/p\u003e \u003cp\u003eSchema Drift and Output Parsing Failures 237\u003c\/p\u003e \u003cp\u003eEvaluation Gaps 237\u003c\/p\u003e \u003cp\u003eLegal and Regulatory Surprise 238\u003c\/p\u003e \u003cp\u003eSummary 238\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 AI for Code Generation and Developer Tools 239\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eSetting Up and Using PACE 240\u003c\/p\u003e \u003cp\u003eInstallation 241\u003c\/p\u003e \u003cp\u003eThe Interface 241\u003c\/p\u003e \u003cp\u003eUsing PACE 241\u003c\/p\u003e \u003cp\u003eAdding Your Own Features 242\u003c\/p\u003e \u003cp\u003eWriting Prompt Templates for Common Coding Tasks 243\u003c\/p\u003e \u003cp\u003eViewing the Built-In Prompts 243\u003c\/p\u003e \u003cp\u003eExplaining Code 244\u003c\/p\u003e \u003cp\u003eGenerating Function Stubs 245\u003c\/p\u003e \u003cp\u003eError Helpers 246\u003c\/p\u003e \u003cp\u003eAdding Comments 246\u003c\/p\u003e \u003cp\u003eOptimization Suggestions 247\u003c\/p\u003e \u003cp\u003eAutomating Repetitive Work with Prompts 248\u003c\/p\u003e \u003cp\u003eGenerating Boilerplate 248\u003c\/p\u003e \u003cp\u003ePerforming Refactors 249\u003c\/p\u003e \u003cp\u003eSuggesting Reviews and Improvements 250\u003c\/p\u003e \u003cp\u003eCombining Prompts 251\u003c\/p\u003e \u003cp\u003eWhen Not to Automate 251\u003c\/p\u003e \u003cp\u003ePrompts for Testing and Debugging 251\u003c\/p\u003e \u003cp\u003eGenerating Unit Tests 252\u003c\/p\u003e \u003cp\u003eExplaining Test Failures 252\u003c\/p\u003e \u003cp\u003eDebugging Runtime Issues 253\u003c\/p\u003e \u003cp\u003eSpotting Performance and Security Issues 253\u003c\/p\u003e \u003cp\u003eImproving the Developer Experience Around Testing 254\u003c\/p\u003e \u003cp\u003eCaution: Don’t Overtrust Test Generation 255\u003c\/p\u003e \u003cp\u003eBest Practices for Prompt-Driven Tools 255\u003c\/p\u003e \u003cp\u003eShow a Diff, Not a Blob 255\u003c\/p\u003e \u003cp\u003eRun Formatters and Linters Automatically 256\u003c\/p\u003e \u003cp\u003eKeep Prompts Short, Modular, and Reusable 257\u003c\/p\u003e \u003cp\u003eBe Explicit About Intent and Output 257\u003c\/p\u003e \u003cp\u003eAsk for Multiple Options When Appropriate 257\u003c\/p\u003e \u003cp\u003eLet the Model Say “I Don’t Know” 258\u003c\/p\u003e \u003cp\u003eTreat Prompts Like Code 258\u003c\/p\u003e \u003cp\u003eStart Narrow, Then Generalize 259\u003c\/p\u003e \u003cp\u003eAvoid Prompt Sprawl 259\u003c\/p\u003e \u003cp\u003eDesign for Human Control 259\u003c\/p\u003e \u003cp\u003eBuilding Better Dev Tools 260\u003c\/p\u003e \u003cp\u003eAdd New Prompt Capabilities 260\u003c\/p\u003e \u003cp\u003eImprove the UI 260\u003c\/p\u003e \u003cp\u003eStore Templates Persistently 261\u003c\/p\u003e \u003cp\u003eAdd Support for Other AI Providers 261\u003c\/p\u003e \u003cp\u003eExperiment with Retrieval 261\u003c\/p\u003e \u003cp\u003eShare Prompt Collections 262\u003c\/p\u003e \u003cp\u003eSummary 262\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 Enhancing Search and Recommendations with AI 263\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhy Traditional Search Falls Short 264\u003c\/p\u003e \u003cp\u003eVector Search and Embeddings 264\u003c\/p\u003e \u003cp\u003eBuilding a Vector Search Demo with Embeddings 266\u003c\/p\u003e \u003cp\u003eStep 1. Prepare the Project 266\u003c\/p\u003e \u003cp\u003eStep 2. Create a Utility for Similarity 267\u003c\/p\u003e \u003cp\u003eStep 3. Build the Index 267\u003c\/p\u003e \u003cp\u003eStep 4. Implement Search 268\u003c\/p\u003e \u003cp\u003eStep 5. Try It Out 269\u003c\/p\u003e \u003cp\u003eReranking with LLMs 269\u003c\/p\u003e \u003cp\u003eConversational Search 271\u003c\/p\u003e \u003cp\u003ePersonalized Recommendations 272\u003c\/p\u003e \u003cp\u003eClassic Approaches 272\u003c\/p\u003e \u003cp\u003eAI-Enhanced Recommendations 273\u003c\/p\u003e \u003cp\u003eBuilding a Simple Recommender with Embeddings + User Profiles 273\u003c\/p\u003e \u003cp\u003eStep 1. Prepare the Project 274\u003c\/p\u003e \u003cp\u003eStep 2. Add Utility Functions 275\u003c\/p\u003e \u003cp\u003eStep 3. Embed Items and Save the Index 276\u003c\/p\u003e \u003cp\u003eStep 4. Compute User Vectors 277\u003c\/p\u003e \u003cp\u003eStep 5. Generate Recommendations 278\u003c\/p\u003e \u003cp\u003eStep 6. Add “Why This” Explanations 280\u003c\/p\u003e \u003cp\u003eDynamic Personalization 281\u003c\/p\u003e \u003cp\u003eEvaluation and Feedback Loops 282\u003c\/p\u003e \u003cp\u003eHybrid Approaches 282\u003c\/p\u003e \u003cp\u003eIntroduction to FUSE 283\u003c\/p\u003e \u003cp\u003eInstalling and Launching FUSE 284\u003c\/p\u003e \u003cp\u003eHow It Works 284\u003c\/p\u003e \u003cp\u003eComparing Search Modes 284\u003c\/p\u003e \u003cp\u003ePersonalization in Action 286\u003c\/p\u003e \u003cp\u003eExperimenting with Retrieval and Ranking 286\u003c\/p\u003e \u003cp\u003eSummary 287\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart IV Business Considerations 289\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 12 Ethical Considerations and Pitfalls 291\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBias and Fairness in Generative AI 291\u003c\/p\u003e \u003cp\u003eReal-World Impacts 292\u003c\/p\u003e \u003cp\u003eMitigation Strategies 293\u003c\/p\u003e \u003cp\u003eTest with Synthetic Users 294\u003c\/p\u003e \u003cp\u003eApply Prompt Engineering to Steer Outputs Toward Inclusivity 294\u003c\/p\u003e \u003cp\u003eBuild User Controls and Transparency Mechanisms 294\u003c\/p\u003e \u003cp\u003eUse Models or APIs with Fairness Tuning or Moderation Filters 296\u003c\/p\u003e \u003cp\u003eDeveloper’s Responsibility 298\u003c\/p\u003e \u003cp\u003eDocument Observed Biases 298\u003c\/p\u003e \u003cp\u003eProvide Mechanisms for User Feedback and Correction 299\u003c\/p\u003e \u003cp\u003eTreat Fairness Testing as a Continuous Process 299\u003c\/p\u003e \u003cp\u003eDefine Fairness Metrics and Conduct Regular Audits 299\u003c\/p\u003e \u003cp\u003eBuild Diverse Teams and Invest in Ethics Training 300\u003c\/p\u003e \u003cp\u003eHandling Fabrication and Misinformation 300\u003c\/p\u003e \u003cp\u003eWhy Fabrication Happens 301\u003c\/p\u003e \u003cp\u003eNext-Token Prediction, Not Truth Seeking 301\u003c\/p\u003e \u003cp\u003eGaps in the Training Data 302\u003c\/p\u003e \u003cp\u003eAmbiguous or Overly Broad Prompts 302\u003c\/p\u003e \u003cp\u003eRisks to Applications 302\u003c\/p\u003e \u003cp\u003eLegal and Compliance Issues 303\u003c\/p\u003e \u003cp\u003eLoss of User Trust 303\u003c\/p\u003e \u003cp\u003eAmplification of Conspiracy Theories and Harmful Misinformation 303\u003c\/p\u003e \u003cp\u003eMitigation Strategies 303\u003c\/p\u003e \u003cp\u003eGround Outputs in Real Data 304\u003c\/p\u003e \u003cp\u003eConstrain the Scope and Encourage Abstention 304\u003c\/p\u003e \u003cp\u003eBuild a Human-in-the-Loop Review 304\u003c\/p\u003e \u003cp\u003eLabel Outputs Clearly 304\u003c\/p\u003e \u003cp\u003eSecurity and Privacy Concerns 305\u003c\/p\u003e \u003cp\u003eKey Risks 305\u003c\/p\u003e \u003cp\u003ePrompt Hacking 306\u003c\/p\u003e \u003cp\u003ePrompt Injection 306\u003c\/p\u003e \u003cp\u003ePrompt Leaking 307\u003c\/p\u003e \u003cp\u003eJailbreaking 307\u003c\/p\u003e \u003cp\u003eEthical vs. Malicious Prompt Hacking 307\u003c\/p\u003e \u003cp\u003eMitigation Strategies 308\u003c\/p\u003e \u003cp\u003ePrevent Data Leakage 309\u003c\/p\u003e \u003cp\u003eDefend Against Prompt Injection 309\u003c\/p\u003e \u003cp\u003eProtect Training Data and RAG Pipelines 310\u003c\/p\u003e \u003cp\u003eMitigate Caching Risks 311\u003c\/p\u003e \u003cp\u003eRegulatory and Compliance Issues 311\u003c\/p\u003e \u003cp\u003eGeneral Data Protection Regulation (GDPR) 311\u003c\/p\u003e \u003cp\u003eEU AI Act 312\u003c\/p\u003e \u003cp\u003eOther Legal Considerations 313\u003c\/p\u003e \u003cp\u003eIndustry-Specific Regulations 313\u003c\/p\u003e \u003cp\u003eFinance 314\u003c\/p\u003e \u003cp\u003eHealthcare 314\u003c\/p\u003e \u003cp\u003eEducation 314\u003c\/p\u003e \u003cp\u003ePractical Steps for Developers 314\u003c\/p\u003e \u003cp\u003eDeveloper’s Ethical Checklist 315\u003c\/p\u003e \u003cp\u003eSummary 316\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 13 Monetizing AI Features 317\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eUnderstanding AI Feature Costs and Value 317\u003c\/p\u003e \u003cp\u003eEstimating the Per-Use Cost of ToasterBot Deployment 318\u003c\/p\u003e \u003cp\u003ePer-Use Cost Components Breakdown 318\u003c\/p\u003e \u003cp\u003eExample: Cost of a Single Chat Session 321\u003c\/p\u003e \u003cp\u003eCost Comparison: API-Based vs. Self-Hosted Deployment 323\u003c\/p\u003e \u003cp\u003ePricing Strategies: Cost-Based vs. Value-Based 325\u003c\/p\u003e \u003cp\u003eCost-Based Pricing 325\u003c\/p\u003e \u003cp\u003eValue-Based Pricing 325\u003c\/p\u003e \u003cp\u003eWhen and How to Charge for AI Features 326\u003c\/p\u003e \u003cp\u003eTiered Subscription Models 326\u003c\/p\u003e \u003cp\u003eUsage-Metering and Rate Limits 327\u003c\/p\u003e \u003cp\u003ePaywall Strategies 329\u003c\/p\u003e \u003cp\u003eValue Communication and Pricing Iteration 330\u003c\/p\u003e \u003cp\u003eIndirect Monetization of AI Features 330\u003c\/p\u003e \u003cp\u003eImplementation and Engineering Considerations for Monetization 331\u003c\/p\u003e \u003cp\u003eAPI Usage Tracking and Token Counting 331\u003c\/p\u003e \u003cp\u003eEnforcing Limits and Feature Gating 335\u003c\/p\u003e \u003cp\u003eIntegrating Billing and Payments 337\u003c\/p\u003e \u003cp\u003eArchitecture Example: Implementing Monetization 337\u003c\/p\u003e \u003cp\u003eCost Modeling and Forecasting in Code 338\u003c\/p\u003e \u003cp\u003eApplying Monetization Strategies to Example Apps 340\u003c\/p\u003e \u003cp\u003eSimpleBot\/ToasterBot: AI Chatbot 340\u003c\/p\u003e \u003cp\u003eSPOT: Structured Prompt Output Toolkit 341\u003c\/p\u003e \u003cp\u003ePACE: Prompt-Augmented Coding Environment 342\u003c\/p\u003e \u003cp\u003eFUSE: Find, Understand, Search, Enhance 343\u003c\/p\u003e \u003cp\u003eSummary 344\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 14 Successful AI-Powered Products 345\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eCase Studies 345\u003c\/p\u003e \u003cp\u003eUps Orion 346\u003c\/p\u003e \u003cp\u003eNuance DAX: Ambient Clinical Documentation 346\u003c\/p\u003e \u003cp\u003eReal-World Examples of AI-driven Applications 347\u003c\/p\u003e \u003cp\u003eAudioPen 348\u003c\/p\u003e \u003cp\u003eConsensus 350\u003c\/p\u003e \u003cp\u003eHumata 351\u003c\/p\u003e \u003cp\u003eEightify 353\u003c\/p\u003e \u003cp\u003eScribe 354\u003c\/p\u003e \u003cp\u003eTability 356\u003c\/p\u003e \u003cp\u003etl;dv 357\u003c\/p\u003e \u003cp\u003eLessons Learned from Successful Implementations 358\u003c\/p\u003e \u003cp\u003eStart with User-Centric Problems 359\u003c\/p\u003e \u003cp\u003eIntegrate AI into Existing Workflows 359\u003c\/p\u003e \u003cp\u003eKeep Humans in the Loop 359\u003c\/p\u003e \u003cp\u003ePrioritize Transparency, Ethics, and Data Responsibility 359\u003c\/p\u003e \u003cp\u003eScale Compound Impact 360\u003c\/p\u003e \u003cp\u003eClose the Feedback Loop 360\u003c\/p\u003e \u003cp\u003eBalance Automation with Creativity 360\u003c\/p\u003e \u003cp\u003eFuture Trends 360\u003c\/p\u003e \u003cp\u003eExplosive Growth of Generative AI Adoption 361\u003c\/p\u003e \u003cp\u003eRising Investment in AI 361\u003c\/p\u003e \u003cp\u003eSynthetic Data and Privacy-Enhancing Technologies 361\u003c\/p\u003e \u003cp\u003eData-Mesh Architectures and Real-Time Analytics 362\u003c\/p\u003e \u003cp\u003eAgentic AI Assistants 362\u003c\/p\u003e \u003cp\u003eMultimodal GenAI 363\u003c\/p\u003e \u003cp\u003eThe Perceive → Reason → Act Loop 363\u003c\/p\u003e \u003cp\u003eModality Abstractions and Adapters 364\u003c\/p\u003e \u003cp\u003eMemory, Retrieval, and Cross-Modal Indexing 365\u003c\/p\u003e \u003cp\u003eFallback Logic and Graceful Degradation 365\u003c\/p\u003e \u003cp\u003eSafe Tool Invocation and Audit Wrappers 366\u003c\/p\u003e \u003cp\u003eOrchestration and Multiagent Coordination 366\u003c\/p\u003e \u003cp\u003eRegulatory and Ethical Considerations 367\u003c\/p\u003e \u003cp\u003eHuman–AI Collaboration 367\u003c\/p\u003e \u003cp\u003eSustainability and Efficiency 367\u003c\/p\u003e \u003cp\u003eSummary 367\u003c\/p\u003e \u003cp\u003eIndex 369\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Computer science [\u003ca title=\"See our other books on Computer science\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Computer%20science%20%5BUY%5D%22\"\u003eUY\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley","offers":[{"title":"Brand New","offer_id":52474949370136,"sku":"9781394373130","price":41.29,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781394373130.jpg?v=1785801696","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/a-developers-guide-to-integrating-generative-ai-into-applications-paperback-softback-9781394373130","provider":"Freshly Printed Books","version":"1.0","type":"link"}