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
"What would a personal cheer team that wants you to grow and blossom look and feel like? Is that the future of design ops?"
Sahibzada Mayed Lauren LinCultivating Design Ecologies of Care, Community, and Collaboration
October 4, 2023
"Lead with the ask, lead with the value, so people understand what you’re looking for from the start."
Frank DuranPartnership Playbook: Lessons Learned in Effective Partnership
January 8, 2024
"People in some countries are three times more likely to buy a product if it’s localized in their language."
Nancy DouyonWe'll Figure That Out in the Next Launch: Enterprise Tech's Nobility Complex
June 15, 2018
"Unmanaged challenges reduce the quality of life in society."
Onur Kocan Ayhan EnsiciUnderstanding the Strategy for Civic Design in a Complex City: Istanbul
November 16, 2022
"One day we were in the office, the next day suddenly remote—there was no choice but to adapt."
Rusha SopariwalaRemote, Together: Craft and Collaboration Across Disciplines, Borders, Time Zones, and a Design Org of 170+
June 9, 2022
"The SIR model is simple but can be applied beyond viruses—to information spread, finance, and UX adoption."
Scott PlewesWhy Isn't Your UX Approach Going Viral?: A Mathematical Model
March 28, 2023
"Retrofitting accessibility at a later date is difficult, costly, and demoralizing."
Sam ProulxAccessibility: An Opportunity to Innovate
September 8, 2022
"We wanted people to get value from day one so they could see how much more they would get from all insights centralized."
Michelle Bejian Lotia Anne-Marie MorellRolling Out a Repository: How Zapier Centralizes Insights from Across their Organization
March 28, 2023
"Facilitation is essential—not just for design work but to build alignment and manage people."
Amy Jiménez Márquez Michael J. Metts Joie ChungThe Atypical UX Manager Path
July 23, 2020
