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
"You have to prepare research to withstand scrutiny by anyone so your team can go forward confidently."
Anna Avrekh Dr. John Pagonis Klara Pelcl Sina SchreiberExpert Panel: Leading in and with Research
March 10, 2022
"We can't say with certainty what needs or pain points we missed when our recruits weren't demographically diverse."
Megan CamposWhat Did I Miss? The Hidden Costs of Deprioritizing Diversity in User Research
March 12, 2021
"Employees that have a work best friend have a 50% drop in turnover risk and are 300% more likely to say they love their companies."
Kat VellosOpener: The Other L Word
January 8, 2024
"Use different words. If somebody has a terrible experience of work labeled a certain way, it’s really hard to use that label without bringing those experiences back."
Adrian HowardSturgeon’s Biases
September 25, 2024
"How we orient ourselves to the future impacts how we experience the present."
Nicole AleongFuture Orientations to Everyday Life: Futures Anthropology as a Methodology
March 26, 2024
"I have learned not to hold on too tightly to the ideas I’ve constructed about myself."
Tamara HaleWar Stories LIVE! Tamara Hale
March 30, 2020
"Minimizing harm protects institutions, not people."
Rachael Dietkus, LCSWThe power to heal and harm
March 13, 2025
"People in organizations are already, to some extent, out there talking to users."
Steve PortigalLooking Back…to Look Ahead
March 26, 2024
"The Step Up for PTSD Virtual Walk exceeded its goal of 2,700 participants, with more than 30,000 app downloads for the event."
Megan Nipe Lyndsay BoothHuman-Centered Design for Engagement: Maturing from Newsletterville to Personalized, One-to-One Messaging
December 8, 2021