Rosenverse
Optimizing AI Conversations: A Case Study on Personalized Shopping Assistance Frameworks

This video is only accessible to Gold members. Log in or register for a free Gold Trial Account to watch.

Log in Register

Most conference talks are accessible to Gold members, while community videos are generally available to all logged-in members.

Optimizing AI Conversations: A Case Study on Personalized Shopping Assistance Frameworks

Gold
Tuesday, June 10, 2025 • Designing with AI 2025

This video is featured in the Designing with AI 2025 playlist.

Share the love for this talk
Optimizing AI Conversations: A Case Study on Personalized Shopping Assistance Frameworks
Speakers: Kritika Yadav
Link:

Summary

The Challenge Users engaging with the AI shopping assistant often felt constrained by limited options, excessive follow-up questions, and a lack of personalization. These shortcomings led to user fatigue, misunderstandings, and a subpar shopping experience. Insights from user research (UXR) and transcripts revealed that users wanted more intuitive, human-like interactions that catered to their unique needs. The Solution A robust, adaptable framework was designed to transform AI conversations into sales-like consultations. By breaking user queries into three core components—use-case, constraints, and preferences—the framework enabled the bot to understand intent and deliver relevant, personalized results. Key enhancements included: Allowing users to skip questions and navigate freely. Providing contextual help for technical queries. Transitioning to open-ended interactions after gathering essential details to prevent over-questioning. Displaying diverse and curated results aligned with user preferences.

Key Insights

  • Traditional conversational AI severely limits visual bandwidth compared to traditional e-commerce interfaces, hindering effective product exploration.

  • The catalog exploration paradox highlights the tension between rich visual browsing and conversational limitations in AI assistants.

  • The expectation gap occurs when AI fails to understand cultural or contextual nuances, eroding user trust and satisfaction.

  • User queries vary widely in specificity; treating all queries the same is a missed opportunity in AI design.

  • Structuring user queries into use case, constraints, and preferences enables AI to perform intelligent reasoning like a skilled salesperson.

  • Carefully crafted prompt design, rather than large-scale fine tuning, can effectively guide LLM reasoning for better conversational AI.

  • Adaptive questioning avoids unnecessary or repetitive queries, improving user experience and reducing frustration.

  • Designing conversational AI as reasoning systems rather than linear scripted flows fundamentally improves interaction quality.

  • A multidisciplinary team combining design, data, and engineering perspectives was crucial to solving this AI conversation challenge.

  • Shifting from seeing AI as a task execution tool to a trusted, empathetic guide changes user perception and engagement positively.

Notable Quotes

"We are designing how the assistant is trying to reason, moving from scripting responses to orchestrating the AI's cognitive process."

"It's not just about fixing the chatbot, it's about bridging the gap between user expectations and actual experiences."

"LLMs don't just match keywords or labels. They infer meaning, extract subtle nuances, and understand intent behind words."

"The catalog exploration paradox shows how current conversational AI restricts browsing and comparison, creating uncertainty."

"Users frequently felt overwhelmed and misunderstood; this was a significant barrier to a positive shopping experience."

"What if we actively taught the model how to break down and analyze queries like a skilled salesperson would?"

"The AI assistant starts with reasoning and not results, engaging users in intelligent conversation to understand needs."

"Don't design for a response, design for reasoning. Teach AI to think critically, analyze information, and arrive at logical conclusions."

"The assistant asks open-ended questions that focus on what truly matters: performance, budget, and preferences."

"We saw a 2.5 times increase in active monthly users and a 1.5 times increase in purchases attributed to the AI assistant."

Ask the Rosenbot
Daniel J. Rosenberg
Digital Medicine Design
2019 • Enterprise Community
JD Buckley
COMMUNICATE: Discussion
2018 • Enterprise Experience 2018
Gold
Joerg Beringer
Scaling User Research with AI: Continuous Discovery of User Needs in Minutes
2025 • DesignOps Summit 2025
Gold
Ned Gartside
Navigating accessibility and climate
2024 • Climate UX Interest Group
Dalia El-Shimy
So You've Got a Seat at the Table. Now What?
2020 • Advancing Research 2020
Gold
Theresa Marwah
How Atlassian is Operationalizing Respect in Research
2020 • Advancing Research Community
Davis Neable
How to Drive a Design Project When you Don’t Have a Design Team
2021 • Design at Scale 2021
Gold
Anat Fintzi
Delivering at Scale: Making Traction with Resistant Partners
2022 • Design at Scale 2022
Gold
Joseph Williams
Unlocking impact and influence through inclusive hiring in research
2021 • Advancing Research Community
Tatyana Mamut
Opening Keynote: Breaking Conway's Law--or How to Work Differently and Not Ship Your Org Chart
2019 • Enterprise Experience 2019
Gold
Megan Blocker
What UX research maturity looks like and how we get there [Advancing Research Community Workshop Series]
2023 • Advancing Research Community
James Wieselman Schulman
Research is a team sport: advancing the work when everyone does the research
2026 • Advancing Research 2026
Gold
Jon Fukuda
Storytelling for DesignOps
2023 • DesignOps Community
Feleesha Sterling
Building a Rapid Research Program
2023 • Enterprise Community
Jonathon Colman
How to Maximize the Impact of Content Design
2024 • DesignOps Summit 2020
Gold
Christopher Taylor Edwards
Design as a Team Practice, A Practical Guide to Cross-functional Collaboration
2021 • DesignOps Summit 2021
Gold

More Videos

Jack Behar

"Interactions are exposed as events on components, so you can define that on clicking a button, a dialog opens."

Jack Behar

How to Build Prototypes that Behave like an End-Product

December 6, 2022

Dan Willis

"The more specific a story gets, the more universal the themes are felt by everybody."

Dan Willis

Enterprise Storytelling Sessions

June 3, 2019

Sam Proulx

"Remote testing helps get closer to real-world results because users are in environments customized for them."

Sam Proulx

SUS: A System Unusable for Twenty Percent of the Population

June 9, 2021

Dave Malouf

"Sometimes it’s easier to say what DesignOps isn’t than what it is."

Dave Malouf Patrizia Bertini Jon Fukuda

The Past, Present, and Future of DesignOps: a 2-part DesignOps Community Call (Part 2)

April 28, 2022

David Eisner

"Less handoff and more collaboration is becoming possible by bringing designers into the workflow with AI assistance."

David Eisner Changying (Z) Zheng Amelia Wattenberger Elyse Holladay

From prototype to production: Vibe coding design for real engineering systems

June 10, 2026

Christopher Taylor Edwards

"Designing as a team means centering all the humans involved, not just the users."

Christopher Taylor Edwards Valerie Roske

Design as a Team Practice, A Practical Guide to Cross-functional Collaboration

September 30, 2021

Victor Udoewa

"Cultural and experiential knowledge are greater than institutional knowledge."

Victor Udoewa

Radical Participatory Research: Decolonizing Participatory Processes

March 9, 2022

Chris Govias

"Too often RFPs ask us to deliver things instead of solve problems."

Chris Govias Mai-Ling Garcia Emily Lessard

Perspectives on Civic Design

September 23, 2021

Ali Jeffery

"Sustainability is not just about the environment, it’s about community."

Ali Jeffery Sheri Chudow

How DesignOps Helped Enable Wall Street to Work Remotely

October 22, 2020