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
Marjorie Stainback
Transforming Strategic Research Capacity through Democratization
2019 • DesignOps Summit 2019
Gold
Candace Myers
Standardizing Design at Scale
2022 • DesignOps Summit 2022
Gold
Prerna Makanawala
Achieving Balanced Design Consistency
2021 • Design at Scale 2021
Gold
Sara Asche Anderson
Not Your Ordinary Re-Brand: Design's Path to Driving Customer Obsession at Best Buy
2024 • Enterprise Experience 2020
Gold
Sam Proulx
Online Shopping: Designing an Accessible Experience
2023 • Design in Product 2023
Gold
Jon Fukuda
Theme 3 Intro
2024 • DesignOps Summit 2024
Gold
Matt Webb
Context Window: Five Futures for AI
2025 • Designing with AI 2025
Gold
Victor Udoewa
Beyond Methods and Diversity: The Roots of Inclusion
2024 • Advancing Research 2024
Gold
Tutti Taygerly
Make Space to Lead
2021 • Design at Scale 2021
Gold
Bria Alexander
Reflect and Chart Forward
2021 • Civic Design 2021
Gold
Julie Baher
Culture Change—My Journey
2015 • Enterprise UX 2015
Gold
Tricia Wang
From Users to Shapers of AI: The Future of Research
2024 • Advancing Research 2024
Gold
Peter Van Dijck
Designing AI-first products on top of a rapidly evolving technology
2025 • Designing with AI 2025
Gold
Tricia Wang
Spatial Collapse: Designing for Emergent Culture
2024 • Enterprise Experience 2020
Gold
Patrick Commarford
Design Staffing for Impact
2024 • DesignOps Summit 2020
Gold
Leisa Reichelt
Opening Keynote: Operating in Context
2018 • DesignOps Summit 2018
Gold

More Videos

Joshua Graves

"The best solutions come from good questions and sitting with the problem, not rushing to fix."

Joshua Graves

We Need To Talk: Addressing Unmet Expectations (Part 2 of 3)

April 28, 2025

Uday Gajendar

"Craft is a pet issue for me; it remains central even in massive enterprise projects."

Uday Gajendar

Theme 1: Introduction

June 9, 2021

Audrey Crane

"Shadow design is not about blaming people—it’s about recognizing that design work is happening outside the design team."

Audrey Crane

Shadow Design–Where Else is Design Happening in Your Organization?

April 20, 2023

Gina Mendolia

"Grandmas provide grounding, resilience, and long-term perspective often through rituals and storytelling."

Gina Mendolia

Therapists, Coaches, and Grandmas: Techniques for Service Design in Complex Systems

December 3, 2024

Sheri Byrne-Haber

"Accessibility isn't about dumbing down interfaces; except for color, most guidelines do not require changing the look or behavior of components."

Sheri Byrne-Haber

The Importance of Accessible Design Systems

January 8, 2024

"A 5% increase in quality experience resulted in a 25 to 85% increase in profitability across industries."

How to Identify and Increase your "Experience Quotient"

June 15, 2018

Adel Du Toit

"User obsession became a strategic goal after making data available and showing progress to leadership including our CFO."

Adel Du Toit

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

June 10, 2022

Kavana Ramesh

"Watching users navigate with assistive technology exposes you to barriers that people with disabilities face online."

Kavana Ramesh

Meaningful inclusion: Practicing accessibility research with confidence

September 24, 2024

Tricia Wang

"All of our spaces have crumpled and collapsed onto each other — that’s the mess we’re living in right now."

Tricia Wang

Spatial Collapse: Designing for Emergent Culture

January 8, 2024