Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
This video is featured in the AI and UX playlist and 1 more.
Summary
Enthusiasm for AI tools, especially large language models like ChatGPT, is everywhere, but what does it actually look like to deliver large-scale user-facing experiences using these tools in a production environment? Clearly they're powerful, but what do they need to make them work reliably and at scale? In this session, Sarah provides a perspective on some of the information architecture and user experience infrastructure organizations need to effectively leverage AI. She also shares three AI experiences currently live on Microsoft Learn: An interactive assistant that helps users post high-quality questions to a community forum A tool that dynamically creates learning plans based on goals the user shares A training assistant that clarifies, defines, and guides learners while they study Through lessons learned from shipping these experiences over the last two years, UXers, IAs, and PMs will come away with a better sense of what they might need to make these hyped-up technologies work in real life.
Key Insights
-
•
Everything chatbots are overly ambiguous and difficult to optimize effectively.
-
•
Targeted AI applications tailored to specific user tasks work better and reduce risk.
-
•
The 'ambiguity footprint' helps product teams assess AI feature complexity along multiple axes.
-
•
Application context and whether AI features are critical or complementary impacts their ambiguity.
-
•
Visible AI interfaces set different user expectations compared to subtle or invisible AI features.
-
•
Prompt design strongly shapes AI behavior, even with similar interfaces delivering very different outputs.
-
•
Dynamic context injection into models adds power but significantly increases development complexity.
-
•
Consistent, thorough evaluation is essential but often neglected in AI application development.
-
•
Data privacy and ethical considerations restrict access to usage data, impeding evaluation efforts.
-
•
Incrementally building AI capabilities on less ambiguous features trains organizational muscles needed for more complex AI.
Notable Quotes
"You’re building three apps in a trench coat with a kind of iffy interface slapped on top of it."
"Chat really isn’t necessarily the best interface for lots of user tasks."
"We tend to see PMs and designers converging on a single everything chatbot, which I find insufficient."
"Ambiguity is inherent when working with AI, but that doesn’t mean you have to accept all of it."
"If you haven’t planned for evaluation, you end up eyeballing the results, which absolutely does not work."
"Responsible AI practices and legal reviews at Microsoft saved us from launching dangerous ambiguous features."
"The bigger and more ambiguous is not always better in AI applications."
"Very similar interfaces can conceal extremely different AI prompts, which shape the outputs."
"Dynamic context is more powerful but adds a ton of stuff to build, making AI development trickier."
"Many organizations just ask around and call it good when evaluating AI models, which is not sufficient."
Or choose a question:
More Videos
"Leaders should change incentive structures to reward strategic design because without incentives nothing improves."
Catt SmallMoving from Execution to Strategy as a Designer
December 6, 2022
"You cannot sleep on your job; the design operating model must continuously evolve and be communicated."
Sabrina Mach Nina WainwrightHow to Design Your Design Operating Model
September 29, 2021
"As a design leader, you must keep everyone moving in the same direction, despite complex tasks and high emotional stakes."
This Game is Never Done: Design Leadership Techniques from the Video Game World
November 6, 2017
"We were changing people’s relationship with change in a rules-based government culture."
Alison Rand Sarah BrooksScaling Impact with Service Design (Videoconference)
March 25, 2021
"Hiring is a two-way street; we have to explain why they want to come join Citrix, like a startup with big company security."
Catherine CourageThe Enterprise UX Journey: Lessons From the Voyage & The Opportunity Ahead
May 13, 2015
"The biggest pain point across organizations is how to make meetings more productive and reduce their volume."
Group Activity: Making Sense of DesignOps
November 7, 2017
"Cohort-based communities let people level up together instead of learning in isolation."
Wendy JohanssonAn Education on Design Education for Orgs
June 10, 2021
"Lauren Cantor is our conference librarian, who keeps all links and resources organized so we don’t have to Google during sessions."
Bria AlexanderOpening Remarks
March 29, 2023
"Bringing stakeholders to observe user sessions helps them see that user-centered design isn’t just a cult."
Mackenzie Cockram Sara Branco Cunha Ian FranklinIntegrating Qualitative and Quantitative Research from Discovery to Live
December 16, 2022