UX for AI : a framework for designing AI-driven products / by Greg Nudelman ; with Daria Kempka, contributing editor

Format:

Book

Author/Creator:

Nudelman, Greg, author.

Contributor:

Kempka, Daria, editor.

Language:

English

Subjects (All):

User-centered system design.

Artificial intelligence.

Physical Description:

1 online resource (xxxii, 314 pages) : illustrations

Place of Publication:

Newark : John Wiley & Sons, Incorporated, [2025]

Summary:

Learn to research, plan, design, and test the UX of AI-powered products Unlock the future of design with UX for AI--your indispensable guide to not only surviving but thriving in a world powered by artificial intelligence. Whether you're a seasoned UX designer or a budding design student, this book offers a lifeline for navigating the new normal, ensuring you stay relevant, valuable, and indispensable to your organization. In UX for AI: A Framework for Designing AI-Driven Products, Greg Nudelman--a seasoned UX designer and AI strategist--delivers a battle-tested framework that helps you keep your edge, thrive in your design job, and seize the opportunities AI brings to the table. Drawing on insights from 35 real-world AI projects and acknowledging the hard truth that 85% of AI initiatives fail, this book equips you with the practical skills you need to reverse those odds. You'll gain powerful tools to research, plan, design, and test user experiences that seamlessly integrate human-AI interactions. From practical design techniques to proven user research methods, this is the essential guide for anyone determined to create AI products that not only succeed but set new standards of value and impact. Inside the book: Hands-on exercises: Build your confidence and skills with practice UX design tasks like Digital Twin and Value Matrix, which you can immediately apply to your own AI projects. Common AI patterns and best practices: Explore design strategies for LLMs (Large Language Models), search engines, copilots, and more. Proven user research strategies: Learn how to uncover user needs and behaviors in this brave new world of AI-powered design. Real-world case studies: See how simple, practical UX approaches have prevented multimillion-dollar failures and unlocked unprecedented value. Perfect for any UX designer working with AI-enabled and AI-driven products, UX for AI is also a must-read resource for designers-in-training and design students with an interest in artificial intelligence and contemporary design.

Contents:

Introduction

References

How to Use This Book

If You Only Have a Couple of Hours

Do the Exercises

Draw in Pencil on Sticky Notes

Part 1 Framing the Problem

Chapter 1 Case Study: How to Completely F*ck Up Your AI Project

A Boiling Pot of Spaghetti

Fail #1: Try to Replace a Trained Expert with AI

Fail #2: Forget About Cost vs. Benefit

Fail #3: No ML Training Data? No Problem!

Fail #4: It Makes No Difference What Question Your AI Model Is Answering

Fail #5: Don't Worry About User Research-You Have an SME!

Final Thoughts

Reference

Chapter 2 The Importance of Picking the Right Use Case

Presuming That AI Will Be Telling Experts How to Do Their Job Is a Red Flag

Ask a Better Question

Chapter 3 Storyboarding for AI Projects

Why Bother with a Storyboard?

How to Create a Storyboard

Establishing Shot

Things

People

Faces

Transitions

Storyboard Conclusion

Storyboarding for AI

Design Exercise: Create Your Own Storyboard

Storyboarding Exercise Example: Death Clock

Chapter 4 Digital Twin-Digital Representation of the Physical Components of Your System

Digital Twin of a Wind Turbine Motor

The Digital Twin Is an Essential Modeling Exercise for Designing AI-Driven Products

How to Build a Digital Twin: An Example

Wait, There's More!

Design Exercise: Create Your Own Digital Twin

Reflect

Design Exercise Example: Life Clock Digital Twin

Chapter 5 Value Matrix-AI Accuracy Is Bullshit. Here's What UX Must Do About It

The Big Secret

Confusion Matrix: How Can Accurate AI Be Wrong?

Value Matrix: The AI Tool for the Real World.

Training AI on Real-Life Outcomes to "Think" Like a Human

One More Example

Final Thoughts: The Importance of Human Cost/Benefit

Design Exercise: Create Your Own Value Matrix

Design Exercise Example: Life Clock Value Matrix

Part 2 AI Design Patterns

Chapter 6 Case Study: What Made Sumo Copilot Successful?

Strong Use Case

Clear Vision

Dedicated Full-Screen UI

AI-Driven Autocomplete

Next-Steps Suggestions

Final Words

Chapter 7 UX Best Practices for SaaS Copilot Design

The More Important the Task, the More Real Estate Is Required

Side Panel

Large Overlay

Full Page

SaaS Copilot Is Stateful

Specialized Fine-Tuned ChatGPT Model

Plug-Ins: Integrated Continuous Learning About Your Specific System

The IA of the AI Is Straightforward, Focused on Chat

Promptbooks: No Need to Twist into Pretzels to Write Prompts

Design Exercise: Create Your Own Mobile Copilot

Design Exercise Example: Life Clock Copilot

Chapter 8 Reporting-One of the Most Important Copilot Use Cases

Zoom AI Companion

Meeting Summary

Answer Questions About the Meeting

Set It and Forget It

UI Modality Switch

Microsoft Security Copilot

Executive Summary: A General Report

Pinboard: A Specialized Report Focused Only on Selected Key Details

Info for Report: Ignore Automatically vs. Pick Manually?

Security and Privacy

Design Exercise: Create Your Own Copilot Report

Design Exercise Example: Life Clock Copilot Report

Daily Report

Weekly Report

Chapter 9 LLM Design Patterns

Restating

Auto-Complete

Talk-Back

Initial Suggestions

Next Steps

Regen Tweaks

Guardrails

Design Exercise: Try Out the LLM Patterns

Design Exercise Example: "Life Copilot Plus"

Chapter 10 Search UX Revolution: LLM AI in Search UIs.

The Current State of Search

Google Search

Amazon Search

The "Mysteries That Are Not Scary" Problem

Enter LLMs

Design Exercise: Design Your Own LLM Search UI

Design Exercise Example: Life Copilot LLM Search

Chapter 11 AI-Search Part 2: "Eye Meat" and DOI Sort Algorithms

What Are Dynamic Dashboards?

Beware of Bias in AI Recommendations

DOI: Degree of Interest/Sort Algorithms

Design Exercise: Create Your Own Dynamic Dashboards and Sort UI

Chapter 12 Modern Information Architecture for AI-First Applications

Design Pattern du Jour: The Canvas

Is Information Architecture Dead?

Amazon.com: Conventional Approach

"AI-Minus"? Homepage

Conventional Search Results Page

AI-Plus Item Detail Page

Conventional Maintenance Pages

AI-First Amazon.com Redesign

AI-First Analysis Overview Page

AI-First Category Analysis Pages

AI-First LLM Search

AI-First Item Detail

AI-First Maintenance Pages

Long Live Information Architecture!

Chapter 13 Forecasting with Line Graphs

Linear Regression

R-Squared

R vs. R-Squared

Forecasting with AI

Nonlinear Regression

Seasonality

Forecasting an Aggregate Variable

Design Exercise: Design Your Own Forecasting UI

Design Exercise Example: Life Clock Forecasting

Chapter 14 Designing for Anomaly Detection

Why Is Detecting Anomalies Important?

Four Main Anomaly Types

Point Anomaly

Change Point Anomaly

Contextual Anomaly

Curve Shape Anomalies

Design Exercise Example: Life Clock Anomaly Detection UI

Getting Ready for AI-pocalypse: Shorthand UX Design Notation as AI Prompt

Shorthand UX Design Notation

Shorthand Notation as AI Prompt to Go Directly to Working Code

What Is Human Work?

Chapter 15 UX for Agentic AI

What Are AI Agents?.

How Do AI Agents Work?

Use Case: CloudWatch Investigation with AI Agents

Part 3 Research for AI Projects

Chapter 16 Case Study: MUSE/Disciplined Brainstorming

Design Idea #1

Design Idea #2

Design Idea #3

Design Idea #4

Design Idea #5

But Wait, Did You Catch That?

Design Exercise: Create Your Novel Designs Using Bookending

Design Exercise Example: Novel Design Ideas for Life Clock

Chapter 17 The New Normal:AI-Inclusive User-Centered Design Process

In the Beginning …

The Monkey or the Pedestal?

A New Way of User-Centered Thinking

What the Heck Is a Spike?

What Is the Role of Data?

Where Is the Customer in All This?

Why Is This Change Necessary?

How Does This Affect the Role of UX?

Does This Mean I Have to Learn About AI So That I Can Ask My Data Science Teammates Good Questions?

Final Handoff to Dev

Many More Changes to Come

Chapter 18 AI and UX Research

UX Techniques That Will Likely See Full Automation

Routine Usability Studies

Routine NPS Studies and Surveys

Collecting and Organizing the Research Data

Triangulation of Quantitative and Qualitative Insights

UX Techniques That Will Be Radically Augmented

Competitive Analysis

Identification of Novel Use Cases

RITE Studies

UX Techniques That Will Become Increasingly Valuable

Core Skills

Workshop Facilitation

Formative Research, Field Studies, Ethnography, and Direct Observation

Vision Prototyping

Augmenting the Executive Strategy

AI Bullshit

AI Strategic Analysis Tools That Replace Humans in Coming Up with Novel Ideas and Business Use Cases

AI Heuristics Analysis Replacing User Research and Design

AI Acting as "Synthetic Users" for the Purposes of Usability Research

Build Your Persona Using AI

Final Words.

References

Chapter 19 RITE, the Cornerstone of Your AI Research

RITE Study vs. Usability Test

#1: RITE Studies Form the Core of the Design Process. Usability Tests Are Often Treated as QA

#2: RITE Studies Demand the Simplest Appropriate Prototypes That Change Rapidly. Usability Tests Often Mean Fancy Rigid Prototypes

#3: RITE Studies Produce Solutions. Usability Tests Produce Reports

A Fringe Benefit of RITE Studies

How to Conduct a RITE Study

A Few More RITE Rounds

The RITE Design Evolution

Dear Future: AI-Assisted RITE Methodology

Design Exercise: Run Your Own RITE Study

Part 4 Bias and Ethics

Chapter 20 Case Study: Asking Tough Questions Through Vision Prototyping

Chapter 21 All AI Is Biased

What Do You Expect When You Ask for "Biologist"?

How About "Basketball Player"?

Third Time's the Charm: "Depressed Person"

Chapter 22 AI Ethics

Chapter 23 UX Is Dead. Long Live UX for AI!

AI Is Happening for Us, Not to Us

Staying on the Rollercoaster Is Optional

"UX Elitism" Is Over

Designers Are "Ambassadors of Innovation"

Core Skills Are in Demand

Combine Low-Fi UX Tools and Sophisticated AI Models

AI Is a "Wicked Problem"

AI Is Just Too Important to Be Left to Data Scientists

The Best AI is Augmented Intelligence.

Notes:

Description based on publisher supplied metadata and other sources.

Includes bibliographical references and index.

ISBN:

1394352271

9781394352272

1394345933

9781394345939

OCLC:

1518770003