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.
Hands-on AI #1: Let’s write your first AI eval
This video is featured in the Evals + Claude playlist.
Summary
If you’re a product manager, UX researcher, or any kind of designer involved in creating an AI product or feature, you need to understand evals. And a great way to learn is with a hands-on example. In this talk, Peter Van Dijck of the helpful intelligence company will walk you through writing your first eval. You will learn the basic concepts and the tools, and write an eval together. This talk is hands on; you can follow along, and there will be plenty of time for questions. You will go away with an understanding of the basic building blocks of AI evals, and with the confidence that you know how to write one. And more importantly, you’ll build some intuition, some product sense, around how the best AI products today are built, and how that can help you use them more effectively yourself.
Key Insights
-
•
Evals consist of a task, a golden dataset with known correct outputs, and an evaluator that measures correctness.
-
•
Manual AI prompt testing is slow and inconsistent; automated evals accelerate and scale evaluation.
-
•
UX and product teams can and should learn evals as a practical, non-technical skill.
-
•
Creating your own golden dataset is essential and cannot be outsourced or fully automated.
-
•
Models are fixed once trained; improvements happen by refining prompts and context design, not retraining the model.
-
•
Evaluations measure task performance, not the underlying model itself, allowing comparison across models.
-
•
Outputting a confidence score from models is unreliable due to lack of internal memory and inconsistent scale interpretation.
-
•
Biases are baked into models during training via evals used in post-training refinement.
-
•
LLMs can be used to judge other LLM outputs to evaluate tasks with non-binary answers.
-
•
Effective eval work requires collaboration across data analysts, engineers, subject matter experts, and UX/product teams.
Notable Quotes
"Evals are like a way to define what good looks like."
"The model was baked and once it’s baked, it does not learn again until they bake a new one."
"You need to be looking at the data. Nobody wants to, but that’s core work."
"Without a golden dataset, you have to build the golden dataset yourself."
"We’re not teaching the model anything; we’re improving our prompts and context."
"Confidence scores from the model are not a good idea because the model has no memory."
"Biases are baked in through the evals used during model training and post-training."
"LLMs judging other LLMs might sound crazy, but if you do it right, it works."
"Evals are a product and UX skill; learning them lets you make these systems do what you want."
"There is a large and growing capability overhang in these models we haven’t discovered yet."
Or choose a question:
More Videos
"Being nice and empathetic at the executive level is critical to get results and maintain trust."
Ted NewardTheme 4: Enterprise Organizational Journey
June 4, 2019
"If design isn’t moving the needle on business strategy, designers feel disempowered and are often first to be cut."
Alfred KahnA Seat at the Table: Making Your Team a Strategic Partner
November 29, 2023
"EMRs and EHRs have terrible user experience and are ripe for design innovation, similar to FinTech years ago."
Theresa NeilDesigning for Wellness: Specializing in Healthcare
May 22, 2024
"When you start concept testing, be clear about what parts of the concept describe the what, the why, and the how."
Michaela MoraAdvanced Concept Testing Approaches To Guide Product Development and Business Decisions
March 11, 2022
"People are better equipped to decide and act in their lives when we deliver relevant and useful information."
Patrick Boehler Madison KarasThe service shift: transforming media organizations to create real value through design
November 19, 2025
"Our one metric that mattered was maximizing the number of VOС-tagged tickets solved – showing customer feedback made it to the roadmap."
Shipra KayanHow we Built a VoC (Voice of the Customer) Practice at Upwork from the Ground Up
September 30, 2021
"I use a very robotic kind of unnatural sounding voice because I want to listen as fast as possible for efficiency."
Samuel Proulx Laur BaekInclusive Research: Debunking Myths and Getting Started
March 12, 2025
"Adversity is part of the human condition—what matters is how we face it, because that gives life greater meaning."
Brendan JarvisIt was the Best of Times. It was the Worst of Times.
September 25, 2024
"Community engagement is a powerful lever often left out of systems thinking processes."
Sheryl CababaExpanding Your Design Lens with Systems Thinking
February 23, 2023
