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
"Clear is kind — clarity and kindness in content design create meaningful experiences for all."
Frances Yllana Ann Buechner Jess Jones Betsy RamacciaD.E.A.R.R. Diaries (Discipline, Experience, Architecture, Reflection + Revolution)
November 16, 2022
"The waters of operations can feel incredibly murky and the path forward may not always be clear."
Bria AlexanderTheme Two Intro
September 8, 2022
"Doing no harm is a core tenet of user experience research, whether or not you are trained in IRB processes."
Dr. Jamika D. BurgeBroad Strokes: Connecting Design, Research, and AI to the World Around Us
June 7, 2023
"Our brains are wired for efficiency and use heuristics, so they prefer daydreaming over hard conversations."
Joshua GravesWe Need To Talk: Navigating Conversations with Your Boss (Part 1 of 3)
April 14, 2025
"Europe has leaned more into public sector service design work, which impacts the kinds of metrics and approaches seen in the book."
Lavrans Løvlie Ben ReasonAsk me anything – Authors of Service Design: From Insight to Implementation
November 19, 2025
"I want researchers in the room in positions of power and influence to help executives see the broader social implications of technology."
Rebecca BuckMission: Keep Talent in Research Roles!
March 10, 2021
"Creating a set of experience KPIs allows us to measure whether our experiences are simple, honest, and meeting customer expectations."
Sarah WilliamsVerizon_A Framework for CX Transformation
January 8, 2024
"No need to take notes — our scribe David Nicholson is capturing detailed session notes and insights for you."
Bria AlexanderOpening Remarks
September 9, 2022
"Customer obsession is actually one of our key values, which makes my job as a researcher a little bit easier."
Joanna Vodopivec Prabhas PokharelOne Research Team for All - Influence Without Authority
March 9, 2022
