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
Jay Bustamante
Navigating the Ethical Frontier: DesignOps Strategies for Responsible AI Innovation
2023 • DesignOps Summit 2023
Gold
Roy Opata Olende
How Zapier Uses ‘All Hands Research’ to Increase Exposure to Users
2020 • Advancing Research Community
Surya Vanka
Unleashing Swarm Creativity to Solve Enterprise Challenges
2021 • Design at Scale 2021
Gold
Christian Crumlish
AMA with Christian Crumlish, author of Product Management for UX People
2022 • Enterprise Community
Alan Williams
Designing essential financial services for those in need
2022 • Civic Design Community
Chris Moses
Stretching the Definition of DesignOps with Product Development
2018 • DesignOps Summit 2018
Gold
Dan Willis
Theme 3: Intro
2024 • Enterprise Experience 2020
Gold
Chui Chui Tan
Global insights: Embracing international and intercultural research for innovation
2025 • Advancing Research 2025
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
John Maeda
About Design Organizations
2019 • DesignOps Community
Candace Myers
Standardizing Design at Scale
2022 • DesignOps Summit 2022
Gold
Yulya Besplemennova
[Demo] Stress-testing GenAI in user research synthesis
2024 • Designing with AI 2024
Gold
Jennifer Strickland
Adopting a "Design By" Method
2021 • Civic Design 2021
Gold
Lavrans Løvlie
Ask me anything – Authors of Service Design: From Insight to Implementation
2025 • Advancing Service Design 2025
Conference
Maverick Chan
From Doodle to Demo: AI as Our Storytelling Partner
2025 • Rosenfeld Community
Crystal Philcox
The Many Faces of Operations
2017 • DesignOps Summit 2017
Gold

More Videos

Doug Powell

"Everything is a prototype."

Doug Powell

Closing Keynote: Design at Scale

November 8, 2018

Mila Kuznetsova

"Giving parents something meaningful to do during sessions helps keep them engaged and supportive."

Mila Kuznetsova Lucy Denton

How Lessons Learned from Our Youngest Users Can Help Us Evolve our Practices

March 9, 2022

Sarah Gallimore

"If we’re really centering it on people and experiences, consider life before place, and place before technology."

Sarah Gallimore

Inspire Progress with Artifacts from the Future

November 18, 2022

Lada Gorlenko

"We never compromise on the business goals, but how we achieve them can be flexible and pragmatic."

Lada Gorlenko Sharbani Dhar Sébastien Malo Rob Mitzel Ivana Ng Michal Anne Rogondino

Theme 1: Discussion

January 8, 2024

Alnie Figueroa

"Start tinkering, playing around, and pushing AI’s limits because the industry shift is going to get faster."

Alnie Figueroa

The Future of Design Operations: Transforming Our Craft

September 10, 2025

Landon Barnes

"If you measure an infinite number of customers, every change would be statistically significant, but not every change would be meaningful."

Landon Barnes

Are My Research Findings Actually Meaningful?

March 10, 2022

Emily Eagle

"Sometimes we have to murder our darlings—let go of favorite parts to let the story or design grow."

Emily Eagle

Can't Rewind: Radio and Retail

June 3, 2019

Malini Rao

"Managing resistance is mental; customers might resist because they've learned workarounds with legacy systems."

Malini Rao

Lessons Learned from a 4-year Product Re-platforming Journey

June 9, 2021

Asia Hoe

"Project management was focused on outputs, assuming the correct feature was already defined."

Asia Hoe

Partnering with Product: A Journey from Junior to Senior Design

November 29, 2023