Building the Rosenbot
Summary
A 30-minute deep-dive into the building of the Rosenbot. We’ll get both hands-on practical and likely a bit philosophical. What does it take to build a useful AI assistant? What does it mean for a business, strategically? And how do we make sure we are building the future that we want, while doing all this? Take-aways: What does strategy look like in an AI world? What does eval-first mean? What the hell is going on deep inside an LLM? And what does all that mean for the future we want to build?
Key Insights
-
•
Generative AI is a new design material requiring fresh approaches distinct from prior UX methods.
-
•
Rose Bot leverages retrieval augmented generation to semantically search Rosenfeld’s extensive UX content.
-
•
Conversation logic beyond the LLM is essential to route, classify intents, and ensure safe responses.
-
•
Evaluation (eval) of AI is fundamentally challenging due to its non-deterministic input and output.
-
•
Effective evaluation requires combining human expert and end-user feedback alongside automated tools.
-
•
A third of a project’s budget and time should be dedicated solely to rigorous AI evaluation.
-
•
‘Prompt deep dive’ usability testing spends extended time on individual prompts to deeply understand interactions.
-
•
New tooling is emerging specifically for tracing conversations, prompt engineering, and observability in AI.
-
•
UX roles remain vital in AI development by inventing new research techniques and ensuring user-centered design.
-
•
Co-creation between users and technology defines how AI applications evolve and succeed or fail.
Notable Quotes
"When GPT came out, my kids immediately adopted it at school and couldn’t pry it from their dead hands."
"This AI stuff is a new design material, just like the internet or mobile was before."
"The Rose Bot has read everything—every piece of Rosenfeld’s knowledge—to help users access it."
"Building generative AI tools is not scary, it’s just very different from the last 20 years of building products."
"There’s a lot of steps behind the scenes to make conversations useful and safe."
"Eval is the engineering word for evaluation, but also what researchers and UX designers naturally do."
"Without proper evaluation, you’re just building a demo – demos are easy, quality production is hard."
"We invented the ‘prompt deep dive’ technique to spend lots of time on one prompt to deeply understand it."
"Co-creation between users and technology determines if this AI evolves to be useful or harmful."
"We should feel okay to throw away old assumptions and tooling and invent new techniques for this new world."
Or choose a question:
More Videos
"Adding inclusivity to the career ladder took three years and this is still a living document with room for change."
Laine Riley ProkayHow DesignOps can Drive Inclusive Career Ladders for All
September 30, 2021
"If diversity alone made research inclusive, then police could never be anti-black because they include black officers."
Victor UdoewaBeyond Methods and Diversity: The Roots of Inclusion
March 26, 2024
"With great power comes great responsibility — that's our foundational context in exploring AI and ML."
Husani OakleyTheme Three Intro
June 6, 2023
"Changing outcomes means changing incentives on all fronts to shift the culture effectively."
Jess GrecoCreating a Basis for Change: Scaling Design Maturity
June 8, 2022
"AI clustering gives a first stab at themes, but you have to move things around yourself."
Shipra KayanMake your research synthesis speedy and more collaborative using a canvas
January 24, 2025
"The focus is on helping teams take better decisions, not handholding them through every step."
Prayag Narula Abhinav KrishnaDialing for Research: How to Reach the Unreachable
March 10, 2022
"The most important thing you can do is listen and watch and put assumptions aside about what is easy or hard."
Sam ProulxUnderstanding Screen Readers on Mobile: How And Why to Learn from Native Users
June 6, 2023
"Change is messy and it can be uncomfortable, much like baking bread—it’s hard to imagine sticky dough turning into a perfect loaf."
Amy EvansHow to Create Change
September 25, 2024
"In enterprise, we’re moving from systems of record, to systems of engagement, to systems of assets where context drives experience."
Greg PetroffEverything is About to Change: Software as Material
June 8, 2016
Latest Books All books
Dig deeper with the Rosenbot
What challenges do AI hallucinations present, and how should designers handle factual reliability?
What new workflows or tools have been effective in bridging the gap between design, engineering, and product teams using AI?
What strategies help uncover unique or surprising insights from qualitative data when using AI?