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
"You don’t want to give too many options like rating from one to ten because consistency gets lost between different LLM calls."
Peter Van DijckBuilding impactful AI products for design and product leaders, Part 2: Evals are your moat
July 23, 2025
"The tapestry exhibition will be a three-dimensional map co-created with refugees and local school kids to reflect their stories."
Xenia Adjoubei Sean BruceEmpowering Communities Through the Researcher in Residence Program
March 29, 2023
"The phone itself is almost the center of the automotive ecosystem on the way to work."
James RamptonThe Basics of Automotive UX & Why Phones Are a Part of That Future
July 25, 2024
"User Interviews offers multi-country recruitment at the same price, supporting Canada, UK, Germany, Australia, and South Africa."
Lily Aduana Savannah Hobbs Brittany Rutherford5 Reasons to Bring Your Recruiting in-House (and How To Do It)
March 12, 2021
"I’m excited about scaling our research work with better ops support and building tools to share knowledge more efficiently."
Kayla Farrell Chelsey Glasson Sean Fitzell Jared LeClercWhat It's Like To Be a User Researcher at Compass
March 12, 2021
"I recommend asking about user needs rather than disability, like whether someone needs captions or larger fonts."
Kate KalcevichIntegrating Accessibility in DesignOps
September 23, 2024
"Our role as designers and researchers will be to determine what not to design to preserve human culture and values."
Ovetta SampsonResearch in the Automated Future
March 11, 2022
"Reflect on what you experienced internally and externally to sharpen and reveal new insights."
Deanna MitchellDesigning with culture: Unlocking impactful insights for Product and UX
March 12, 2025
"Knowledge is not only intended for human consumption, it is meant for human action."
Ren PopeBuilding Experiences for Knowledge Systems
June 6, 2023
