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.

Coffee with Lou #4: Taking a Peek Under the Rosenbot's Hood (Videoconference)
Friday, June 14, 2024 • Rosenfeld Community
Share the love for this talk
Coffee with Lou #4: Taking a Peek Under the Rosenbot's Hood (Videoconference)
Speakers: Peter Van Dijck and Louis Rosenfeld
Link:

Summary

What happens when you cross an eager librarian, a happy puppy, and 800 UX experts? You get the Rosenbot—Rosenfeld's new GPT-4 level chatbot, trained on our books and hundreds of hours of conference and community call recordings. What went into creating the Rosenbot? Lou is joined by SimplyPut's Peter van Dijck, an old friend from the IA community and the chief architect of the Rosenbot. If you're beginning your journey into developing generative AI products, you'll want to join Lou and Peter to learn from their lessons, ask questions, and share your own thoughts on AI's role in making curated content more useful and impactful.

Key Insights

  • Building effective AI chatbots requires substantial investment in evaluation—often 30-50% of total project time and budget—to ensure quality, safety, and usefulness.

  • The Rosenbot is trained on highly curated Rosenfeld Media content, avoiding outdated or contradictory material common to most organizational knowledge bases.

  • The chatbot is explicitly designed to credit the human authors and experts behind the content to maintain transparency and respect for intellectual property.

  • Rather than summarizing entire books, the Rosenbot delivers insights linked to sources, encouraging users to explore original works and supporting book sales.

  • Conversational memory is simulated by summarizing prior dialogue and feeding it back into the model, as current large language models lack intrinsic memory.

  • Evaluation requires both end-user feedback and expert review since users might be satisfied with inaccurate or incomplete answers.

  • There is a persistent challenge in balancing the presentation of evergreen knowledge with content currency given constantly evolving methodologies and societal norms.

  • AI can surface relevant historical context, but nuanced interpretation and linking of evolving methodologies likely require human curation or 'knowledge historians'.

  • Expanding the interface beyond the traditional conversational model with interactive widgets can enhance user interaction, yet is still underexplored.

  • Analytics on chatbot queries can reveal trends in users’ interests and help authors understand how their work is being referenced and applied.

Notable Quotes

"You can’t read it all or watch it all yourself, but now we have technology that can make that useful—like a community memory for our content."

"A very large percentage of the project should be focused on evaluation, sometimes 30 to 50 percent of time and budget."

"The large language model itself does not have memory, so we summarize previous dialogue and feed it back to simulate memory."

"We’ve trained it not to summarize books to avoid cannibalizing book sales; it’s a tool to promote discovery and connection to content."

"Evaluations need both end users and experts because an answer that makes a user happy can be objectively wrong."

"The content we provide is all curated and high quality, unlike typical intranet or company content that’s often outdated or conflicting."

"This product is not perfect but might be the best there is for UX and product content at this point—about 60% there, aiming for 80%."

"Methodologies and societal understandings change, so the system needs to surface changes over time, connecting older ideas to newer ones."

"The idea of a conversational interface shouldn’t constrain us; adding widgets or interactive elements is definitely possible."

"If you don’t jump in and build this stuff, all you’ll do is read articles that don’t give you the real understanding."

Ask the Rosenbot
Laine Riley Prokay
Carving a Path for Early Career DesignOps Practitioners
2022 • DesignOps Summit 2022
Gold
Frances Yllana
D.E.A.R.R. Diaries (Discipline, Experience, Architecture, Reflection + Revolution)
2022 • Civic Design 2022
Gold
Cassandra Piester
Developing and Deploying Your Design Operations Strategy
2024 • DesignOps 2024
Gold
Ned Dwyer
The Intersection of Design and ResearchOps
2024 • DesignOps 2024
Gold
Josh Clark
Sentient Design: New Design Patterns for New Experiences (3rd of 3 seminars)
2025 • Rosenfeld Community
Andrew Webster
Scaling Design Capability: How Involved Should You Be?
2021 • DesignOps Summit 2021
Gold
Helen Armstrong
Augment the Human. Interrogate the System.
2023 • Enterprise UX 2023
Gold
Hugh Dubberly
Problems with Problems: Reconsidering the Frame of Designing as Problem-Solving (Videoconference)
2019 • Enterprise Community
Jack Moffett
SAFe or Sorry? (Videoconference)
2019 • Enterprise Community
Jack Moffett
UX Metrics That Matter and The Future of our Design at Scale Conference: A Community Conversation (Videoconference)
2022 • Enterprise Community
Silke Bochat
5 Antifragile Strategies for a DesignOps 2.0
2024 • DesignOps 2024
Gold
Sam Proulx
To Boldly Go: The New Frontiers of Accessibility
2022 • Design at Scale 2022
Gold
Rachael Dietkus, LCSW
Leading through the long tail of trauma (Videoconference)
2022 • Enterprise Community
Sarah Flamion
Complex Problem? Add Clarity by Combining Research and Systems Thinking
2020 • Advancing Research 2020
Gold
Christian Crumlish
Morning Insights Panel
2022 • Design in Product 2022
Gold
Kristen Guth, Ph.D.
Out of the FOG: A Non-traditional Research Approach to Alignment
2023 • Advancing Research 2023
Gold

More Videos

"Being delightful is the only thing a video game does; without delight, the game dies."

This Game is Never Done: Design Leadership Techniques from the Video Game World

November 6, 2017

Abby Covert

"The same diagram hated by New Yorkers in the 1970s can serve as the perfect starting place for New Yorkers of today."

Abby Covert

Stuck? Diagrams Help (Videoconference)

October 27, 2022

Steve Portigal

"There doesn’t have to be a big takeaway; just capture the story and the lesson may come later."

Steve Portigal Susan Simon-Daniels Tamara Hale Randolph Duke II

War Stories LIVE! Q&A-Discussion

March 30, 2020

Kara Kane

"International government design communities can share learnings and scale user-centered design beyond national borders."

Kara Kane

Communities of Practice for Civic Design (Videoconference)

April 7, 2022

Caroline Vize

"Identifying the right success metrics is a major problem because execs often don’t know what to ask for."

Caroline Vize

The State of UX: Five Lessons from 2021 to Accelerate Digital Experience in 2022

March 9, 2022

Lada Gorlenko

"Designers can build government services that prioritize equity and resilience."

Lada Gorlenko

Theme 3: Introduction

June 10, 2021

Jay Bustamante

"Machine learning engineers bring AI to life — they’re responsible for making it real."

Jay Bustamante

Navigating the Ethical Frontier: DesignOps Strategies for Responsible AI Innovation

October 2, 2023

Marjorie Stainback

"We had one researcher for every 10 designers, some groups had one for every 15. It was a little messy."

Marjorie Stainback Kelsey Kingman

Transforming Strategic Research Capacity through Democratization

October 24, 2019

Rachael Dietkus, LCSW

"Design should inherently be ethical and trauma-responsive; trauma-informed should be our default."

Rachael Dietkus, LCSW Uday Gajendar Dr. Dawn Emerick Dawn E. Shedrick, LCSW

Leading through the long tail of trauma (Videoconference)

July 13, 2022