[Demo] Complexity in disguise: Crafting experiences for generative AI features
Summary
- 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."
Or choose a question:
More Videos
"We moved from Evernote to spreadsheets, to a giant affinity board in Mirror, then to UserVoice, and finally to idiomatic software with AI."
Shipra KayanHow we Built a VoC (Voice of the Customer) Practice at Upwork from the Ground Up
September 30, 2021
"Most categories are fuzzy; there’s no clear boundary between what’s in or out."
Peter MorvilleThe Architecture of Understanding
May 13, 2015
"Having those tough conversations with C-Suite execs, delivering findings with unwavering voice because you know the customer."
Renee ReidBecoming a ResearchH.E.R (Highly Enterprise Ready)
June 3, 2019
"The environment can disrupt critical interactions, like when Stacey gets caught up in cords and takes her eyes off the patient."
Dane DeSutterKeeping the Body in Mind: What Gestures and Embodied Actions Tell You That Users May Not
March 26, 2024
"Multiple payment providers aren’t just a feature; they’re an accessibility lifeline for people who can’t read or reach their credit card easily."
Sam ProulxOnline Shopping: Designing an Accessible Experience
October 3, 2023
"Balance UX and CX—making the site work technically is not enough if the content or experience isn’t meaningful."
Andrew Custage Michael MallettThe Digital Journey: Research on Consumer Frustration and Loyalty
March 29, 2023
"Silence is productive—resist the temptation to fill it immediately after asking a question."
Shelby SwitzerMaking Space for Community Knowledge-sharing in a Distributed World
December 10, 2021
"AI can empower researchers to solve pain points — like anticipating trends or critiquing discussion guides — amplifying impact rather than replacing work."
Llewyn PaineCoexisting with AI: A practical guide for researchers to navigate tools, ethics, and integration
March 11, 2025
"The techno-optimist hacker lens believes growth is the only metric that matters, enabling disruption but causing blind spots."
Robin BeersNavigating organizational systems: Rethinking researcher’s role in driving change
March 13, 2025
