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
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 helps us speak in the language and context that motivates each team and stakeholder."
Christian Crumlish Wendy Johansson Rich Mironov Aditi Ruiz Adam ThomasAfternoon Insights Panel
December 6, 2022
"Build a design ops backlog that anyone in the organization can contribute to and you revisit regularly."
Jackie AjouxLeveling-Up: A Single-Player’s Guide to the DesignOps Team-of-One
January 8, 2024
"How do we become facilitators who can encourage and model true power sharing? That’s the big question."
Natalia RadywylCo-Designing New Power in Australia's Public Sector
November 16, 2022
"Instead of playing the melody Miles Davis wrote, the soloist creates a melody spontaneously."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
June 4, 2019
"For some users, AI products are not just tools, they are relationships."
Dane DeSutterKeeping the Body in Mind: What Gestures and Embodied Actions Tell You That Users May Not
March 26, 2024
"Storytelling and facilitation are becoming more important than just hard research skills for driving strategic product decisions."
Jen Cardello Dr. Shadi Janansefat Alex WrightCurating insight: Strategies for integrating knowledge across research functions
March 11, 2025
"Technology can revolutionize how we think about education."
Kristin SkinnerFive Years of DesignOps
September 29, 2021
"That’s the kind of feature that never would have made it to the top of anyone’s backlog without design."
Gretchen AndersonScaling the Human Center
June 8, 2017
"When you see yourself and someone else, you see possibility, and that drives engagement and investment."
Jose Coronado Julie Gitlin Lawrence LipkinPeople First - Design at JP Morgan
June 10, 2021
