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
"Are you creative? Such a loaded question, isn't it?"
Dr. Karl JeffriesThe Science of Creativity for DesignOps
January 8, 2024
"Show them, don’t tell them — involving stakeholders early builds skin in the game and helps control quality."
Amy MarquezINVEST: Discussion
June 15, 2018
"The weakest insight method might win simply because of the relationship to the power structure."
Steve Portigal Chris Chapo Kelly Goto Christian RohrerDiscussion
May 13, 2015
"It took a lot of relationship building and conversations to break down the perception that designers' time was owned by particular teams."
Alicia MootyDesign Staffing Models
September 30, 2021
"I believe there's really no such thing as a boring place at the state of mind."
Ana Maria Montero Barrantes Aditi Dhar Michelle Kaplan Nate Osborne Matt LaurenceThe Authentic UX Talent Show
January 8, 2024
"Field usability testing showed stakeholders immediately how much value UX can add by catching issues before deployment."
Lada Gorlenko Sharbani Dhar Sébastien Malo Rob Mitzel Ivana Ng Michal Anne RogondinoTheme 1: Discussion
January 8, 2024
"We think about research as the magnetic field that attracts every part of the business into alignment around the customer."
Sofia QuinteroThe Product Philosophy Behind EnjoyHQ
March 10, 2021
"Please don’t chop off that engine until the new one is built because you are not the only one on this plane."
Laura KleinUnique challenges of innovation in enterprises
April 23, 2020
"You’ve got to take control of the backlog and position your team as value-driven, not just servicing individual teams."
Andrew MichaelBuilding a Product Insights Team
March 10, 2022
