A Developer's Guide to Integrating Generative AI into Applications.

Format:

Book

Author/Creator:

Minnick, Chris.

Series:

Tech Today Series

Language:

English

Subjects (All):

Generative artificial intelligence.

Computer software--Development.

Computer software.

Physical Description:

1 online resource (417 pages)

Edition:

1st ed.

Place of Publication:

Newark : John Wiley & Sons, Incorporated, 2026.

Summary:

Create, implement, and scale commercially successful generative AI applications that solve real-world problems In A Developer's Guide to Integrating Generative AI into Applications , software developer, technology educator, and author Chris Minnick explain exactly how to design and implement scalable generative AI applications.

Contents:

Cover

Title Page

Copyright Page

About the Author

About the Technical Editor

Acknowledgments

Contents at a Glance

Contents

Introduction

What Does This Book Cover?

Who Should Read This Book

Reader Support for This Book

Part I Foundations of Generative AI

Chapter 1 Introduction to Generative AI

Evolution of AI Applications

Key Eras of AI Development

Logic and Rules-Based Systems

Early Machine Learning

Expert Systems

Big Data and Statistical Machine Learning

Deep Learning

The Rise of Generative AI

Transition to GenAI

Understanding AI and ML

What Machine Learning Can Do

Supervised Learning

Unsupervised Learning

Semi-Supervised Learning

Reinforcement Learning

Self-Supervised Learning

Large Language Models

Tokenization

Embedding

Transformer Layers

Prediction

What Makes Generative AI Different?

Generating Content

GenAI Is Necessarily Unpredictable

GenAI Is Probabilistic

GenAI Requires Prompt Design

GenAI Is Multimodal

GenAI Shifts UX Expectations

GenAI Needs Guardrails

Real-World Examples of AI Integration

AI-Enhanced Customer Service Bots

Generative Writing Tools

Image Generation in Creative Tools

Summary

Chapter 2 Understanding Generative AI Models

Key Factors in Choosing a Model

Cost and Pricing Structure

Licensing Model

Performance Metrics

Suitability for Your Use Case

Technical Features

Architecture

Parameter Count

Training Objective and Data

Fine-Tuning

Context Window

Unique Functionalities

Proprietary Models

GPT (OpenAI)

Claude (Anthropic)

DALL·E (OpenAI)

Gemini (Google DeepMind)

Open and Open-Source Models

OLMo (Allen AI)

Llama (Meta)

Stable Diffusion (Stability AI)

Deciding Between Proprietary and Open Models

When to Use Which Model.

Adapting Your Model's Abilities

Prompt Engineering

Retrieval-Augmented Generation

Choosing the Right Adaptation Strategy

When to Use Non-Generative Models Alongside GenAI

Key Advantages of Non-Generative Approaches

Strategic Use Cases for Hybrid Approaches

Latency-Critical Applications

Cost and Performance Optimization

Preprocessing and Filtering

Decision-Making and Scoring

When to Choose Traditional Approaches Over AI

Chapter 3 Getting Started with AI APIs and SDKs

Exploring Hosted Models

Setting Up a Simple Development Environment

OpenAI Developer Platform

Getting an OpenAI API Key

Anthropic's Build with Claude

Google Gemini Developer API

GenAI Integration Patterns

Common Architectural Models for Integrating GenAI

Backend Service Integration

Frontend-OnlyIntegration

Plugin-BasedIntegration

Hybrid Integration

Model Access Patterns

Synchronous vs. Asynchronous

Streaming vs. Batch

Input Types for GenAI Integration

Plain Text Prompts

Structured Prompts

Multimodal Prompts

Response Handling

Integrating Responses into the User Interface

Logging and Analytics

Chaining Responses to Other Services

Combining Techniques

Chapter 4 AI-Generated Data and Synthetic Users

Generating Test Data with GenAI

Traditional Test Data Generation

Manual Generation

Automated Data Generation

Data Masking

Using GenAI for Test Data Generation

Introducing the Sample App

Techniques for Generating Synthetic Data

Few-Shot Prompting for Schema-Aligned Data

Template-Based Generation with Randomized Inputs

Structured Output Formats

Simulating User Behavior and Interaction Flows

Simulating Chat-Based Interactions

Simulating Navigational Flows and Multistep Interactions.

Simulating Edge Case and Adversarial Behavior

Best Practices and Limitations of Behavior Simulation

Chapter 5 Prompt Engineering

Why Prompt Design Matters in GenAI Applications

Prompt Quality Affects Output Quality

Prompting Is Cheaper and Faster than Fine-Tuning

Prompts Shape the Voice and Tone of AI

Better Prompts Reduce Hallucinations

Prompts Embed Business Logic

Prompt Design Supports Edge Case Handling

Good Prompts Improve Performance and Reduce Cost

Prompt Types

Zero-Shot Prompting

Few-Shot Prompting

Chain-of-Thought Prompting

Prompting Best Practices

Guiding the LLM with System Messages

Prompt Templates for Repeatable Interactions

Adjusting Generation Parameters

Max Tokens

Temperature

Top P

Top K

Stop Sequences

Deciding How to Set Inference Parameters

Tooling for Prompt Development

In-Browser Prompt Playgrounds

Anthropic Workbench

OpenAI Playground

Prompt Management

Part II Designing for a Better AI Experience

Chapter 6 Human-AI Interaction and UX Design

Managing User Expectations

Clarify the AI's Capabilities Up Front

Set Expectations Around Potential Failure

Communicate When Outputs are Probabilistic

Provide Cues that Suggest When the AI is "Thinking"

Use Progressive Disclosure to Build Trust

Avoid Overpromising AI Abilities

Designing Interfaces for AI-Powered Features

Understand the Users and Context

Ensure Clarity of AI-Generated vs. User-Generated Content

Provide Opportunities for Correcting or Refining AI Outputs

Use Visual or Interaction Cues to Indicate When the AI Is Active or Idle

Offer Undo or Step-Back Controls to Reduce Risk and Build Confidence

Design for Uncertainty and Failure

Balancing Automation with Human Control

Improving Over Time.

Capturing and Using User Feedback

Balancing Explicit Ratings and Behavioral Signals

Learning Without Surprising Users

Monitoring for Drift and Relevance

Accessibility and Inclusion in AI UX

Accessibility Standards for AI Applications

Best Practices for Accessible AI UX

GenAI as an Accessibility Aid

Testing GenAI Accessibility

Using GenAI to Test GenAI Outputs

Human-Centered AI in the Real World

Chapter 7 Optimizing AI for Performance and Cost

From Prototype to Production

The Hidden Cost of GenAI Features

Why Optimization Matters

The Trade-Off Triangle

Minimize Latency and Reduce Redundant API Calls

Reduce Prompt Size

Reduce the Size of the Model's Response

Use Caching to Avoid Redundant Calls

Cache Exact Prompt-Response Pairs

Prompt Fingerprint Caching

Reuse Similar Responses with Embedding Search

Parallelize Requests

Stream Responses

Precompute for Known Flows

Lightweight Fine-Tuning

Profile and Monitor Performance

Logging to Identify Latency Hotspots

Observability Tools for GenAI Systems

Handle Rate Limits Gracefully

Understanding Usage Tiers

Throttle and Buffer Requests

Design for Fallback and Graceful Degradation

Part III Integrating AI into Applications

Chapter 8 Building AI-Powered Chatbots and Assistants

Start with a Simple Chatbot

Principles of Conversational Interface Design

Managing Turn-Taking, Flow, and Feedback in Dialogue

Show Feedback and Errors

Temporarily Disable the Input to Prevent Accidental Repeat Submissions

Use Backchannel Cues and Confirmations

Guide the Next Turn

Keep the User Oriented

Handling Memory, Context, and User Personalization

Tracking Conversation History

Adding Basic Personalization

Steering AI Toward Specific Tasks or Domains.

Using System Prompts to Constrain Behavior

Welcoming the User

When to Use RAG for External Knowledge

Adding Auto-Scroll and Streaming Responses

Designing for Fallback, Clarification, and Edge Cases

Clarify Ambiguous Questions

Fall Back When the Answer Isn't Known

Handle Out-of-Scope Requests Gracefully

Best Practices for Customer Service Chatbots

Chapter 9 Generating and Enhancing Content with AI

Building SPOT: Fast, On-Brand, and Grounded

Overview of SPOT

Getting Set Up

Where to Put This in a Real Application

AI-Assisted Writing and Summarization

Going from Brief to Draft

Rewriting for Tone, Audience, and Locale

Summarization with Source Citations

Repurposing Long-Form Content

Choosing the Right Summarization Mode

Keep It On-Brand with the Style Pack

Prompt-Time Injection

Post-Generation Validation

Implementation Patterns for Your Own Apps

Grounded Writing with RAG

Structured Outputs for Pipelines

Evaluation and Human Review

Accessibility and Inclusive Language

Legal, IP, and Disclosure Considerations

AI-Generated Images and Media

Design First, Pixels Second

Maintain Brand Consistency in Visuals

Image Editing Workflows

Audio and Voice Features

Video Workflows: Storyboard First, Shots Second

Measure What Matters

Logging and Provenance for Media

Personalization and Dynamic Content

Understanding the Personalization Spectrum

Defining Your Signals and Features

Runtime vs. Precomputed Variants

Adding Guardrails for Fairness and Safety

Experimenting and Optimizing

Localizing and Adapting Across Cultures

Locale-Specific Spelling and Grammar

Multilingual Prompt Templates

Cultural Norms and Communication Style

Regional Imagery and References

Showing Your Work: UX Patterns for Trust.

Common Pitfalls and How to Avoid Them.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

1-394-37314-7

9781394373147

OCLC:

1572069919