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.
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
"AI struggles with context, taste, and common sense, and designers bring that to the table."
Dan SafferWhy AI projects fail (and what we can do about it)
May 14, 2025
"Concept testing is almost like a mini workshop focusing on the value and benefits of that method."
Dr. Jamika D. BurgeTheme 3 Intro
March 11, 2022
"A Slack bot that sends random customer quotes encourages ongoing learning and discovery."
Crystal YanBuilding a Customer-Centric Culture
March 30, 2020
"Every small initiative can lead to significant change when multiplied across communities."
Ash BrownSilver Linings: What DesignOps Learned in the Shift to WFH
October 23, 2020
"Managing vendors is a full-time job, and research ops teams often coordinate numerous vendors for tools and recruitment."
Kate TowseyThe State of ResearchOps: More Than Just Theory
June 20, 2019
"Tools don't matter as much as the desire to learn and ask why things keep happening the way they do."
Megan Blocker Amy Bucher Katie Hansen Ricardo Martins Nidhi Singh RathoreDay 2 Theme Panel
March 12, 2025
"Being human is the foundation—seeing the person on the other side of the conversation as a human being."
Sara Asche Anderson Jamie KaspszakNot Your Ordinary Re-Brand: Design's Path to Driving Customer Obsession at Best Buy
January 8, 2024
"Green spaces are not luxuries—they're necessities for urban life."
Ali Jeffery Sheri ChudowHow DesignOps Helped Enable Wall Street to Work Remotely
October 22, 2020
"Change is the reason we keep paying attention to stories; without it, there is no story."
Jon FukudaStorytelling for DesignOps
August 17, 2023
