Rosenverse

This video is only accessible to conference ticket holders.

Log in Create account

For 90 days after a conference, only paid ticket holders can watch conference videos. After that, all Gold members have access.

Contact Support if you are having any issues.

Optimizing AI Conversations: A Case Study on Personalized Shopping Assistance Frameworks
Conference ticket
Tuesday, June 10, 2025 • Designing with AI 2025
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

  • Users expect AI to understand nuanced intents but often face poor interactions.

  • Conversational AI must transition from reactive to proactive engagement to reduce user frustration.

  • A collaborative team approach combining various expertise led to a more effective design process.

  • Understanding user behavior through chat logs revealed diverse query types, informing design choices.

  • Designing for reasoning allows AI to provide personalized assistance rather than generic responses.

  • Avoiding unnecessary follow-up questions improves user satisfaction and engagement.

  • A structured framework for AI reasoning can prevent miscommunication and trust issues with users.

  • Qualitative feedback indicated users began to see AI as a trusted guide instead of just a tool.

  • Effective prompt design can significantly enhance an AI's understanding of user intent.

  • Successful AI conversation design can lead to higher conversion rates and improved user experiences.

Notable Quotes

"Designing AI means transforming it from a reactive tool to a proactive guide."

"The fundamental shift in perspective is to think of conversations as complex reasoning systems."

"AI does not just react to keywords; it actively thinks through the conversation."

"Designing for reasoning allows us to create AI assistants that are more flexible and adaptable."

"We need to empower AI to understand the intent behind user queries for effective interactions."

"Users felt empowered to engage in richer conversations when AI understood their needs better."

"The results we've seen show how user satisfaction can dramatically improve with the right design approach."

"We need to teach AI how to think critically, not just respond mechanically."

"It's about enabling the AI to act like a helpful guide rather than just a machine."

"Don't design for a response; design for reasoning."

Kayla Farrell
What It's Like To Be a User Researcher at Compass
2021 • Advancing Research 2021
Gold
Sam Proulx
SUS: A System Unusable for Twenty Percent of the Population
2021 • DesignOps Summit 2021
Gold
Andrew Michael
Building a Product Insights Team
2022 • Advancing Research 2022
Gold
Elana Chapman
Getting started with accessibility research
2025 • Rosenfeld Community
John Taschek
Making People the X-Factor in the Enterprise
2018 • Enterprise Experience 2018
Gold
Bria Alexander
The Big Question about Resilience: A panel discussion
2024 • DesignOps Summit 2024
Gold
Dan Saffer
Why AI projects fail (and what we can do about it)
2025 • Rosenfeld Community
Chelsea Mauldin
Let's Talk About Money
2022 • Civic Design 2022
Gold
Katie Hansen
Finding the unknown in the known: Harnessing meta-analysis and literature review
2025 • Advancing Research 2025
Gold
Rich Mironov
How Can Product Managers and UXers Help Each Other (and Why are Product Folks so Annoying Sometimes)?
2022 • Design in Product 2022
Gold
Greg Petroff
Design is the Differentiator: Bringing New Design Innovations to a Very Antiquated and Very Large Industry
2021 • Design at Scale 2021
Gold
Kate Towsey
Shaping the future of research ops: Expanding roles and strategies for a more integrated research ecosystem
2025 • Advancing Research 2025
Gold
Billy Carlson
Principles of Team Wireframing
2023 • DesignOps Summit 2023
Gold
Mackenzie Guinon
M.C. Escher’s UX Research Career Ladder
2022 • Advancing Research 2022
Gold
Sara Conklin
A UXer’s 12-Month Journey from Climate Concern to Climate Credibility
2025 • Climate UX Interest Group
Ash Brown
Silver Linings: What DesignOps Learned in the Shift to WFH
2020 • DesignOps Summit 2020
Gold

More Videos

Carla Casariego

"Our digital experience team has only existed for three years, so we have a lot of work to do."

Carla Casariego Sarah Spencer

DesignOps in Wonderland

October 24, 2019

Noel Lamb

"If you have the opportunity to snatch up research lab space, do it without hesitation."

Noel Lamb

Cultivating Business Partnerships to Grow Research Ops

March 21, 2022

Chris Moses

"We didn't even start out as a software company. We're actually a birthing clinic."

Chris Moses

Stretching the Definition of DesignOps with Product Development

November 7, 2018

Sara Asche Anderson

"You have to slow down to speed up; understanding the why is crucial before executing the strategy."

Sara Asche Anderson Jamie Kaspszak

Not Your Ordinary Re-Brand: Design's Path to Driving Customer Obsession at Best Buy

January 8, 2024

JJ Kercher

"At this point, your relationships really start extending across all roles."

JJ Kercher

A Roadmap for Maturing Design in the Enterprise

June 15, 2018

PJ Buddhari

"We had to learn to work smarter, not just harder, to support Spectrum."

PJ Buddhari Nate Baldwin

Meet Spectrum, Adobe’s Design System

June 9, 2021

Adrian Howard

"Talking about outcomes first helped question their previous experiences."

Adrian Howard

Sturgeon’s Biases

September 25, 2024

Alla Weinberg

"The nervous system is our personal surveillance system making sure we’re connected and safe."

Alla Weinberg

Design Teams Need Psychological Safety: Here’s How to Create It

September 8, 2022

Greg Petroff

"Solutions are everywhere. We are fortunate to have solutions all around us."

Greg Petroff

Design is the Differentiator: Bringing New Design Innovations to a Very Antiquated and Very Large Industry

June 9, 2021