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.

[Demo] Complexity in disguise: Crafting experiences for generative AI features
Gold
Wednesday, June 5, 2024 • Designing with AI 2024
Share the love for this talk
[Demo] Complexity in disguise: Crafting experiences for generative AI features
Speakers: Trisha Causley
Link:

Summary

AI tools like ChatGPT have exploded in popularity with good reason: they allow users to draft, summarize, and edit content with unprecedented speed. While these generic tools can generate any type of content or perform any type of content task, the user needs to craft an effective prompt to get high-quality output, and often needs to exchange multiple messages with additional guidance and requirements in order to improve results. When you’re building an AI-powered text generation feature, such as a product description or email writer, you typically can’t expect users to craft their own prompts. And unless you’re building a chat interface, you’re unlikely to offer the ability to iteratively improve the output. Instead, your feature needs a robust prompt skeleton that combines with user input to produce high-quality output in a single response. For the designer, this means building an interface that helps users provide the exact information that creates a successful prompt. This process is more complex than simple form design or a mad-lib prompt completion tool. The user input, often including free form text fields, might be required to fill in prompt variables, but it also could change the prompt structure itself, or even override base instructions. The effectiveness of the user input significantly influences the quality of the output, underscoring the need for designers to be deeply familiar with the backend prompt architecture so they can design the frontend. Drawing on recent text generation projects, I'll demonstrate how the interface design can respond to and evolve with the prompt architecture. I’ll talk about how to determine which prompt components to make invisible to the user, which to provide as predefined options, and which should be authored by the user in free-form text fields. Takeaways How prompt structure can impact user interface design and conversely, how design can impact prompt structure Techniques to provide effective user guidance within AI generation contexts to ensure consistently high-quality output Real-world examples and learnings from recent generative AI projects in an e-commerce software product

Key Insights

  • Building specialized AI features requires predefining most of the prompt to guide the LLM effectively rather than having users write their own prompts.

  • Users refine prompts iteratively in chat interfaces, but specialized tools often allow only one shot with limited input variables.

  • Understanding the backend prompt structure is critical for designers to decide which parts are fixed and which are configurable by users.

  • Tone of voice is a complex variable that significantly impacts product description differentiation and brand personality.

  • Free-text inputs for tone proved difficult for users; predefined tone options simplify user choices while maintaining quality.

  • AI models inconsistently detect tone from existing text samples and report high confidence in contradictory results, making this approach unreliable.

  • Successful tone options must be sufficiently distinct to allow users to easily identify and select the best fit for their brand.

  • Embedding detailed tone attribute descriptions (e.g., vocabulary, pronouns, punctuation) in prompts improves AI output quality.

  • The default confident and positive tone of models like ChatGPT may not suit all contexts and needs to be explicitly adjusted in prompts.

  • Providing a minimal, intuitive UI that maps to rich, complex backend instructions balances user simplicity with output quality.

Notable Quotes

"In a chat interface, you’re able to fill in the information that you missed and iterate on the output as it’s being generated."

"When you’re building a specific AI feature, you don’t want to make your user write their own prompt."

"It becomes the designer’s responsibility to figure out what aspects of the instructions to the LLM should be configurable and what should be fixed."

"A prompt is just a set of instructions to an AI in the context of text generation."

"People get stuck during the sessions when asked to describe their brand voice in just one or two words."

"The LLM gave many different answers for the same passage, each time reporting it was one hundred percent confident."

"Tones need to be distinct enough so that merchants can spot the tone that best fits their brand."

"Even though we’ve got a single dropdown field, it maps to a far richer set of instructions in the prompt."

"The confident tone built into these tools may be one of the more problematic features of Gen AI."

"By default, you’re getting I am very confident of my answers."

Ask the Rosenbot
Bas Raijmakers, PhD (RCA)
What Design Research can Learn from Documentary Filmmaking
2022 • Advancing Research 2022
Gold
Jason Mesut
Unmasking Design Leadership: Navigating leadership without neglecting ourselves
2025 • Rosenfeld Community
Theresa Neil
Designing for Wellness: Specializing in Healthcare
2024 • Rosenfeld Community
Mujtaba Hameed
The new horizon of ethnography: using AI to unlock the full potential of in-person research
2026 • Advancing Research 2026
Conference
Matt Bernius
Trauma-informed Research: A Panel Discussion
2021 • Advancing Research Community
Alberto Ferreira
Making it Count: Developing a custom digital metric framework that works
2021 • QuantQual Interest Group
Todd Healy
Driving Change with CX Metrics
2023 • Enterprise UX 2023
Gold
Crystal Yan
Building a Customer-Centric Culture
2020 • Advancing Research 2020
Gold
Chris Geison
Theme 1 Intro
2022 • Advancing Research 2022
Gold
Stefanie Owens
Optimizing for Outcomes: Transformation Design in Systems at Scale
2024 • Advancing Service Design 2024
Gold
Mila Kuznetsova
How Lessons Learned from Our Youngest Users Can Help Us Evolve our Practices
2022 • Advancing Research 2022
Gold
Steve Portigal
Discussion
2015 • Enterprise UX 2015
Gold
Dr. Jamika D. Burge
Advancing the Inclusion of Womxn in Research Practices
2022 • Advancing Research Community
Aiyana Bodi
Three Key Climate Initiatives and How You Can Help
2024 • Climate UX Interest Group
Scher Foord
Turn the Ship Around: How to Apply Design Thinking Across Your Organization
2021 • Design at Scale 2021
Gold
Shipra Kayan
Emerging principles for using AI in Design: What the product design team at Miro has learned from deeply integrating AI in their workflow
2025 • Designing with AI 2025
Gold

More Videos

Giff Constable

"Finance is the common language that all domains can speak, especially critical if you want a seat at the executive table."

Giff Constable

Financial fluency for product leaders: AMA with Giff Constable

April 11, 2024

Kritika Yadav

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

Kritika Yadav

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

June 10, 2025

Alla Weinberg

"Offering anonymity in safety surveys helps people be honest when they don’t feel safe to share openly."

Alla Weinberg

How to Build and Scale Team Safety

January 8, 2024

Harry Brignull

"Systemic deceptive design is harder to regulate because manipulation happens across time and user context."

Harry Brignull Mark Leiser Robert Stribley

Beyond Clicks and Tricks: Why deceptive design has grown into a regulatory faultline

January 16, 2026

Kit Unger

"We’re typically designing products to solve really complex issues."

Kit Unger

Theme 2: Introduction

June 10, 2021

Sofia Quintero

"The biggest mistake in any implementation is ignoring the emotional side of change management."

Sofia Quintero

Beyond Tools: The Messy Business of Implementing Research Repositories

March 10, 2022

Jeff Gothelf

"The hardest part is changing the measure of success from output to outcomes, specifically changes in customer behavior."

Jeff Gothelf

The Intersection of Lean and Design

January 10, 2019

Kit Unger

"In our desire to see the big table, we often forget that sometimes it’s more important not to seek validation at the table but to offer it to someone else."

Kit Unger Lada Gorlenko

Theme 3 Intro

June 10, 2022

Jorge Arango

"We think with things; our brain is part of us but we extend our cognition into our environments and tools."

Jorge Arango

The Best of Both Worlds: How to Integrate Paper and Digital Notes (1st of 3 seminars)

April 5, 2024