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
"A little color purple to start the day. Good morning."
Bria AlexanderOpening Remarks
October 3, 2023
"Public services in the US are harder to design because everything has to have a cost and be paid for."
Ron BronsonDesign, Consequences & Everyday Life
November 18, 2022
"When AI systems become unreliable, we need productive humility in our interfaces and ways to engage human agency."
Josh Clark Veronika KindredSentient Design: New Design Patterns for New Experiences (3rd of 3 seminars)
February 12, 2025
"What am I avoiding? Asking that every day turns out to be a surprisingly powerful prioritization tool."
John Cutler Harry MaxPrioritization for designers and product managers (1st of 3 seminars)
June 13, 2024
"You have to start with users, not the data, and force prioritization to avoid dashboard overload."
Theresa NeilJust Build Me a Dashboard!
April 9, 2019
"We freak out when leadership acts irrationally, but we accept that users do the same because we understand them better."
Peter MerholzThe Trials and Tribulations of Directors of UX
July 13, 2023
"Continuous feedback instead of just end-of-year reviews helps people understand their long-term goals and improve in the moment."
DesignOps and The Great Talent War of 2021
August 19, 2021
"Yesterday we touched upon topics like chatDBT, chatbots, trust, intentionality, agency, and even alien interns."
Uday Gajendar Louis RosenfeldDay 2 Welcome
June 5, 2024
"Model companies are students in a classroom wanting good points—they’re happy to run external expert evals to improve."
Peter Van DijckHands-on AI #2: Understanding evals: LLM as a Judge
October 15, 2025
