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
"Confusing product portfolios often arise when two successful teams’ products overlap, complement, or have vague distinctions."
Jorge ArangoMeeting of the Waters: Designing for Successful Inorganic Growth
August 12, 2021
"UX research marketing is the strategy behind and implementation of intentional effective promotion and communication of who UX research is and what UX research does."
Molly FargotsteinMultipurpose Communication & UX Research Marketing
September 12, 2019
"If you only measure vanity metrics like downloads, you risk tracking numbers that don’t translate to real usage or value."
Saara Kamppari-Miller Nicole Bergstrom Shashi JainKey Metrics: Comparing Three Letter Acronym Metrics That Include the Word “Key”
November 13, 2024
"The code of conduct is on every page of our site; it includes procedures for getting assistance."
Bria AlexanderOpening Remarks
October 3, 2023
"Government is always complex and nonlinear, but digital experiences can and should be cleaner and better."
Angy Peterson Bob AinsburyMore Than Technology: Personalized Public Sector Experiences
December 10, 2021
"Cassandra will share how to balance strategic vision and tactical execution to inspire teams and secure stakeholder buy-in."
Frances YllanaTheme 2 Intro
September 24, 2024
"We are all just modeling. UX researchers and data scientists differ more in language than in practice."
Jennifer FraserWhat would Emmy Noether Do? Math, Models and Mulling in UX Research
March 29, 2023
"Let’s blur the barrier between the outside and the inside, to stop missing out and strengthen the connections critical to what we do."
Mackenzie GuinonM.C. Escher’s UX Research Career Ladder
March 9, 2022
"Investing time upfront in user research and discovery avoids rushed fixes that don’t meet clients’ needs."
Product and Design at Bloomberg: A 15-year Evolution
December 6, 2022
