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
Jemma Ahmed
Democratization: Working with it, not against it [Advancing Research Community Workshop Series]
2024 • Advancing Research Community
Jorge Arango
AI as Thought Partner: How to Use LLMs to Transform Your Notes (3rd of 3 seminars) (Videoconference)
2024 • Rosenfeld Community
Alicia D. Johnson
Disasters and the 21st Century
2021 • Civic Design 2021
Gold
Ariba Jahan
Team Resiliency Through a Pandemic
2024 • DesignOps Summit 2020
Gold
Uday Gajendar
Leading through the long tail of trauma (Videoconference)
2022 • Advancing Research Community
Kayla Farrell
What It's Like To Be a User Researcher at Compass
2021 • Advancing Research 2021
Gold
Saskia Liebenberg
Start Small for Big Impact (Videoconference)
2019 • DesignOps Community
The Many Faces of Operations
2017 • DesignOps Summit 2017
Gold
Alla Weinberg
How to Build and Scale Team Safety
2024 • DesignOps Summit 2020
Gold
Andy Barraclough
From Costly Complexity to Efficient Insights: Why UX Teams Are Switching To Voxpopme
2024 • DesignOps 2024
Gold
Bria Alexander
Opening Remarks
2021 • DesignOps Summit 2021
Gold
Civic Design in 2022 (Videoconference)
2022 • Civic Design Community
Natalia Radywyl
Co-Designing New Power in Australia's Public Sector
2022 • Civic Design 2022
Gold
George Zhang
UX Research Excellence Framework
2021 • Advancing Research 2021
Gold
Russell Blair
[Case study] Killing the blank page
2024 • Designing with AI 2024
Gold
Benjamin Real
Showing the Value of DesignOps by Not Having a DesignOps Team
2020 • DesignOps Summit 2020
Gold

More Videos

Samuel Proulx

"Complexity is not a barrier to accessibility – even the most complicated games have been made accessible."

Samuel Proulx

Invisible barriers: Why accessible service design can’t be an afterthought

December 3, 2024

Courtney Kaplan

"We created an onboarding camp that helped new product team members get up to speed quickly, and then replicated that across groups."

Courtney Kaplan

Taking it to the next level: Career paths in DesignOps

November 8, 2018

Gonzalo Goyanes

"Our aim as design leaders is not only growth but to be an essential part of the company’s strategy."

Gonzalo Goyanes

Design ROI: Cover a Little, Get a Lot

September 8, 2022

Kim Fellman Cohen

"We went back to the beginning of design thinking to stay connected and learn how to shape the future."

Kim Fellman Cohen

Measuring the Designer Experience

October 23, 2019

Sarah Fathallah

"Arnstein’s ladder reduces participation to delegating decision-making power, ignoring safety, well-being, or satisfaction."

Sarah Fathallah

A Typology of Participation in Participatory Research

March 28, 2023

Theresa Marwah

"If participants want us to delete their video, we’re going to delete it, going above legal requirements."

Theresa Marwah

How Atlassian is Operationalizing Respect in Research (Videoconference)

February 27, 2020

Aras Bilgen

"Democratization is the Trojan Horse that poses as fairness for all but is really a cover for the devaluation of professional researchers."

Aras Bilgen Ari Zelmanow

Research Democratization: A Debate

March 29, 2023

Dan Willis

"I’m worried you aren’t up to it, frankly."

Dan Willis

Enterprise Storytelling Sessions

June 8, 2017

Ted Booth

"Only work with the companies that are willing to invest the time needed for meaningful transformation."

Ted Booth Sam Ladner Fredrik Matheson Russ Unger

Discussion

June 8, 2016