GenAI for UXers: A Rosenbot Demo and Discussion
Summary
If you’re a UX practitioner or product designer, there’s a new way to learn your craft: the Rosenbot, a GPT-4 chatbot trained on Rosenfeld’s conferences, books, and more. Aside from being incredibly useful, its focused scope and unusually high degree of content quality impacted the Rosenbot’s design approach in some interesting ways. Join Rosenfeld Media founder Lou Rosenfeld and Rosenbot developer Peter van Dijck for a demo and a dive into the design decisions that drove the Rosenbot’s development.
Key Insights
-
•
Rosenverse combines 20 years of curated UX content into a searchable subscription platform.
-
•
The Rosen Bot is an AI chat bot trained specifically on Rosenfeld Media’s books and conference sessions, enabling focused, high-quality UX answers.
-
•
Books provide richer, semantically denser content for AI retrieval than unstructured conference talks, improving answer quality.
-
•
Contextual navigation via AI-suggested prompts helps users explore deeper topics related to initial queries.
-
•
Defining what constitutes a 'good' AI answer is the hardest challenge, more so than technology or training.
-
•
The AI system is a retrieval-augmented model; it doesn’t train the base LLM but provides additional curated context dynamically.
-
•
The Rosen Bot can generate multi-week training programs based on simple prompts for team learning and development.
-
•
Free and premium tiers exist; gold subscriptions grant access to premium content, discounts, and soon, ebook access.
-
•
Creating playlists with notes is a new feature to support personalized or team-based learning paths.
-
•
The platform champions inclusion, iteration, and collaboration, having worked with over 1100 diverse contributors.
Notable Quotes
"The Rosen Bot is trained on all of our books plus over a thousand recorded sessions from conferences and community talks."
"Books are semantically very rich and thus pull content much more effectively in our vector database than conference talks."
"Nobody really knows what all this AI stuff is about yet, so we’re experimenting with it ourselves."
"We want you to take all AI-generated info with a grain of salt but it gets you part of the way."
"Contextual navigation is really powerful — these AI-generated prompts help you dig deeper into a topic."
"Defining what good looks like for an AI answer is the real work, much more than engineering complexity."
"The AI doesn’t train itself; we provide context dynamically, so it enhances answers with curated data."
"The Rosen Bot can turn a simple prompt into a five-week training program for your team."
"We’ve worked with over 1100 contributors, focusing on inclusion, iteration, and collaboration."
"We want to keep our content evergreen by focusing on people skills and critical thinking, not just tools."
Or choose a question:
More Videos
"Jazz soloists draw from a lifetime of patterns, sometimes quoting TV theme songs like the Muppets or Sanford and Son."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
November 6, 2017
"Inclusion, collaboration, and iteration are the three pillars of how we work with authors to make a book."
Louis RosenfeldCoffee with Lou: Should You Write a (UX) Book?
March 7, 2024
"Building influence has been such a challenging part of growing in my own career. It takes a lot of communication and understanding others’ goals."
Catt Small Micah Bennett Brian Carr Jessica HarlleeWhat's Next for ICs: Exploring Staff and Principal Designer Roles
February 22, 2024
"You might find that spending the most time getting people interested in collaboration is where the work really happens."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"Wonder Studio automatically segments actors, maps their movements to a 3D model, and renders a synthetic avatar video."
Llewyn Paine[Demo] Deploying AI doppelgangers to de-identify user research recordings
June 5, 2024
"Random assignment to treatment or control is essential—if it’s not random, it’s not a true experiment."
Joshua NobleCasual Inference
October 6, 2023
"Choosing the right output depends on the desired outcome—from quick iterations to gaining senior leadership buy-in."
Sara LogelYour Colleagues are Your Users Too
March 29, 2023
"The themes this year include transforming century-old industries, startup to enterprise, the outsider’s perspective, and partnering to transform."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"If you have to learn a workaround, you want to learn it once and reuse it again and again."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023
