Rosenverse

Log in or create a free Rosenverse account to watch this video.

Log in Create free account

100s of community videos are available to free members. Conference talks are generally available to Gold members.

AI in Real Life: Using LLMs to Turbocharge Microsoft Learn
Thursday, February 13, 2025 • Rosenfeld Community

This video is featured in the AI and UX playlist and 1 more.

Share the love for this talk
AI in Real Life: Using LLMs to Turbocharge Microsoft Learn
Speakers: Sarah Barrett
Link:

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."

Ask the Rosenbot
Sahibzada Mayed
Cultivating Design Ecologies of Care, Community, and Collaboration
2023 • DesignOps Summit 2023
Gold
Brigette Metzler
Research Repositories: A global project by the ResearchOps Community (Videoconference)
2020 • Advancing Research Community
Mike Brzozowski
UX in everyday products: Empowering climate conscious choices (Videoconference)
2024 • Climate UX Interest Group (Rosenfeld Community)
Nicole Bergstrom
AccessibilityOps: Moving beyond “nice to have”
2024 • DesignOps Community
Megan Nipe
Human-Centered Design for Engagement: Maturing from Newsletterville to Personalized, One-to-One Messaging
2021 • Civic Design 2021
Gold
Benjamin Real
Maturity Models: A Core Tool for Creating a DesignOps Strategy
2021 • DesignOps Summit 2021
Gold
Cheryl Platz
Merging Improv with Design (Videoconference)
2019 • Enterprise Community
Elena Naids
The Power of Difficult Conversations: A Case Study on How We Introduced Design Ops in the Federal Government Space
2023 • DesignOps Summit 2023
Gold
Max Gadney
Assessing UX jobs for impact in climate
2024 • Climate UX Interest Group (Rosenfeld Community)
Elizabeth Churchill
Exploring Cadence: You, Your Team, and Your Enterprise
2017 • Enterprise Experience 2017
Gold
Amelia Cole
Data-Prompted Interviews
2021 • QuantQual Interest Group (Rosenfeld Community)
Mansi Gupta
Women-Centric Research: What, Why, How
2023 • Advancing Research 2023
Gold
Sam Proulx
SUS: A System Unusable for Twenty Percent of the Population
2021 • Design at Scale 2021
Gold
Sam Proulx
To Boldly Go: The New Frontiers of Accessibility
2022 • DesignOps Summit 2022
Gold
Caroline Jarrett
Have fun with statistics?
2024 • Rosenfeld Community
Bria Alexander
Opening Remarks
2023 • Advancing Research 2023
Gold

More Videos

Catt Small

"Leaders should change incentive structures to reward strategic design because without incentives nothing improves."

Catt Small

Moving from Execution to Strategy as a Designer

December 6, 2022

Sabrina Mach

"You cannot sleep on your job; the design operating model must continuously evolve and be communicated."

Sabrina Mach Nina Wainwright

How 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

Alison Rand

"We were changing people’s relationship with change in a rules-based government culture."

Alison Rand Sarah Brooks

Scaling Impact with Service Design (Videoconference)

March 25, 2021

Catherine Courage

"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 Courage

The 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

Wendy Johansson

"Cohort-based communities let people level up together instead of learning in isolation."

Wendy Johansson

An Education on Design Education for Orgs

June 10, 2021

Bria Alexander

"Lauren Cantor is our conference librarian, who keeps all links and resources organized so we don’t have to Google during sessions."

Bria Alexander

Opening Remarks

March 29, 2023

Mackenzie Cockram

"Bringing stakeholders to observe user sessions helps them see that user-centered design isn’t just a cult."

Mackenzie Cockram Sara Branco Cunha Ian Franklin

Integrating Qualitative and Quantitative Research from Discovery to Live

December 16, 2022