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
"This header took six minutes of IA work—but two years to make happen."
Sarah BarrettThe "How" of Enterprise Information Architecture
June 6, 2023
"Visions capture held knowledge that a team has maybe not been able to yet take action on."
Catt SmallCraft a Vision that Actually Gets Shipped
April 30, 2026
"Don’t lead with salary negotiation; build trust first and then explore possibilities."
Dave Hoffer Joanne WeaverUX Job Search AMA #2 with Joanne Weaver and Dave Hoffer
April 3, 2025
"Research is at its base a sales role, which can be an uncomfortable truth for researchers."
Jane DavisStrategic Shifts and Innovations in User Research: Navigating Challenges and Opportunities
March 11, 2025
"There is always going to be a power gap in inclusiveness efforts unless we critically question who is missing."
Rachael Dietkus, LCSW Llewyn Paine Nishanshi Shukla David WomackAI: Passionate defenses and reasoned critique [Advancing Research Community Workshop Series]
September 18, 2024
"It’s not a fight; it’s about finding that soft spot where people are already trying to do something."
Maria SkaadenPanel Discussion: Methodologies and Work Environments
November 8, 2018
"We don’t want to list every single customer activity; we need to abstract behavior patterns to manage interruptions."
Cheryl PlatzDemystifying Multimodal Design: The Design Practice You Didn't Know You're Doing
April 4, 2024
"Service design does not have an answer for how to handle radically different user needs across communities."
Ron BronsonDesign, Consequences & Everyday Life
November 18, 2022
"If your team sees a clear path of mastery in your organization, they’re much more likely to stay."
Liam ThurstonWhy Your Design Team Is Quitting, And How To Fix It
June 10, 2022
