Rosenverse

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
Panel Discussion: Communicating the Value of DesignOps
2018 • DesignOps Summit 2018
Gold
Yasmine Khan
Checking Bias and Listening to Financially Vulnerable Americans
2020 • Advancing Research 2020
Gold
Cassandra Piester
Developing and Deploying Your Design Operations Strategy
2024 • DesignOps Summit 2024
Gold
Soma Ghosh
What emerging methods are advancing UX research [Advancing Research Community Workshop Series]
2023 • Advancing Research Community
Bria Alexander
Theme Two Intro
2022 • DesignOps Summit 2022
Gold
Andy Barraclough
From Costly Complexity to Efficient Insights: Why UX Teams Are Switching To Voxpopme
2024 • DesignOps Summit 2024
Gold
Uday Gajendar
The Rise of Meta-Design: A Starter Playbook
2022 • Enterprise Community
World Usability Day Panel Discussion
2022 • DesignOps Community
Erin Hoffman-John
This Game is Never Done: Design Leadership Techniques from the Video Game World
2017 • DesignOps Summit 2017
Gold
Maria Giudice
Remaking the Making Company: Moving from Product to Experience
2016 • Enterprise UX 2016
Gold
Ron Bronson
Design, Consequences & Everyday Life
2022 • Civic Design 2022
Gold
Kevin Bethune
Reimagining Design: Unlocking Strategic Innovation
2022 • Design at Scale 2022
Gold
Cheryl Platz
Merging Improv with Design
2019 • Enterprise Community
Shanti Mathew
Civic Design at Scale: Introducing the Public Policy Layer Cake
2021 • Civic Design 2021
Gold
Chris Geison
What is Research Strategy?: A Panel of Research Leaders Discuss this Emergent Question
2021 • Advancing Research Community
Maggie Dieringer
Cutting through the Noise
2020 • DesignOps Community

More Videos

Megan Blocker

"Scrappy grassroots methods never fully go away; you always need to ask where you can get scrappy next."

Megan Blocker

A Selectively Scrappy Approach to ResearchOps

November 8, 2018

Jon Fukuda

"Where else are you gonna hear these stories and learn from all the various corners of our practice?"

Jon Fukuda

Theme 3 Intro

September 25, 2024

Andy Barraclough

"There’s a big merger in this space and two UX giants haven’t been behaving nicely, introducing higher prices and stricter commercial terms."

Andy Barraclough Betsy Nelson

From Costly Complexity to Efficient Insights: Why UX Teams Are Switching To Voxpopme

September 23, 2024

Ben Davies

"It’s not enough to build a repository and expect people to come; you need a distribution strategy to put research where users are."

Ben Davies Matt Duignan Andrew Michael Dr. Emily DiLeo

Expert Panel: The Principles of Research Repository Design

March 11, 2022

Ashley Cortez

"Residents show up with their full selves, wanting solutions for multiple needs, not just the narrow project scope."

Ashley Cortez Devika Menon Nidhi Singh Rathore Danita J. Reese Mari Nakano

Shifting Toward Community-Led Innovation in Local Government

December 8, 2021

Adel Du Toit

"This is not just a typical HR survey; it focuses deeply on the products and experiences employees use daily."

Adel Du Toit

Get Your CFO To Say: 'Our Strategic Goal is User Obsession'

June 10, 2022

Anna Avrekh

"Prioritizing research questions is key because we can’t validate every single detail."

Anna Avrekh

User Research, Design, and Product - A Love Story

March 11, 2021

Kate Kalcevich

"Rapid iteration with three to five user interviews is often enough to inform design and validate accessibility effectively."

Kate Kalcevich

Integrating Accessibility in DesignOps

September 23, 2024

Robin Beers

"You have to understand the power dynamics around the table—seniority, function, gender, skin color, religion—they all matter."

Robin Beers Nalini Kotamraju Andy Warr

Panel: Excellence in Communicating Insights

March 26, 2024