Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
Building impactful AI products for design and product leaders, Part 2: Evals are your moat
This video is featured in the AI and UX playlist.
Summary
The secret ingredient for impactful AI products is “evals”—an architecture for ongoing evaluation of quality. Without evals, you don’t know if your output is good. You don’t know when you’re done. Because outputs are non-deterministic, it’s very hard to figure out if you are creating real value for your users, and when something goes wrong, it’s really tricky to figure out why. Simply Put’s Peter van Dijck will demystify evals, and share a simple framework for planning for and building useful evals, from qualitative user research to automated evals using LLMs as a judge.
Key Insights
-
•
AI product development involves three layers: model capabilities, context management, and user experience, with evals central to experience quality assurance.
-
•
Automated evals help scale testing of AI with inherently open-ended inputs and outputs, enabling faster iteration cycles with confidence.
-
•
LLMs can serve as judges (evaluators) of other LLM outputs, which works because classification is cognitively easier than generation.
-
•
Defining what 'good' means for an AI system is a detailed, evolving process informed by research, domain expertise, and observed risks.
-
•
A three-option evaluation (e.g., yes/no/maybe) works better than fine-grained scales for consistent automated scoring by LLMs.
-
•
Synthetic data, generated by LLMs based on manually created examples, efficiently expands dataset breadth and usefulness.
-
•
Domain experts are essential for tagging data and establishing quality criteria, especially for high-stakes areas like healthcare or legal.
-
•
Building effective evals requires substantial effort—expect 20-40% of project resources devoted to this work.
-
•
Cultural differences impact subjective evals like politeness, requiring localization and careful domain definition.
-
•
AI product quality management is a strategic ongoing commitment, extending beyond initial development into production monitoring and iteration.
Notable Quotes
"AI products almost always have both open-ended inputs and outputs, which makes testing really hard."
"You have to build a detailed definition of what is good for my system to do meaningful automated evals."
"It’s much easier to classify an answer than to generate an answer, and that’s why LLM as a judge works."
"You don’t want to give too many options like rating from one to ten because consistency gets lost between different LLM calls."
"Synthetic data is useful because it’s easier to generate more examples of something you already have than to create entirely new data."
"If you launch in the US and politeness is an issue, first try to fix it with prompts; only if that fails should you build an eval."
"Evals are really your intellectual property—they define what good looks like in your domain."
"Domain experts are crucial for tagging data because users might say ‘that’s great,’ but experts can tell it’s totally wrong."
"You should plan 20 to 40 percent of your project budget on evals—it’s a lot more work than most people expect."
"This is where UX and product strategy bring huge value—defining what good means rather than leaving it to engineers alone."
Or choose a question:
More Videos
"Storytelling became the root of the workshops because it helped everyone relate and respect each other’s experiences."
Florence OkoyeAfroFuturism and UX Research
March 27, 2023
"You get a lot of different research outputs in a matter of minutes from your scope input."
Joerg Beringer Thomas GeisScaling User Research with AI: Continuous Discovery of User Needs in Minutes
June 10, 2025
"Systemic bias means a tendency for procedures and practices within an institution that favors certain social groups over others."
Sandra CamachoCreating More Bias-Proof Designs
January 22, 2025
"Are we excited to go to work in the technology industry to remove jobs and eliminate the human from the equation?"
Sam YenDriving Organizational Change Through Design? Do more of this and less of that
June 9, 2017
"Cybernetics is the discipline of systems with purpose, looking at how a system acts to achieve its goals."
Paul Pangaro, PhDSystems Disciplines: Table Stakes for 21st Century Organizations
June 6, 2023
"Disability isn't rare; one in five people have a disability right now."
Sam ProulxAccessibility: An Opportunity to Innovate
September 8, 2022
"Knowledge management solutions must focus on both the explicit knowledge that can be documented and the tacit knowledge that resides in people’s experiences."
Maria TaylorKnowledge is Power: Managing the Lifeblood of the Design Org
October 3, 2023
"Stop trying to replace researcher with AI."
Daniel Korczynski Justyna ParmeeFrom generic to contextual research insights with AI | Live Q&A
March 11, 2026
"Stability today is more complicated than staying on a fixed path; adaptability and diverse skills bring security."
Ashley SewallExit Interview #5: Designing My Life After Tech
February 19, 2026