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
"Some of the most impactful insights come from data analytics and user research collaborating to find behaviors seen in real people and aggregate data."
Eduardo Ortiz Robin Beers Rachael Dietkus, LCSW Bruce Gillespie Jess Greco Marieke McCloskey Renee ReidDay 3 Theme Panel
March 13, 2025
"Creativity means a change in perception, moving from what is familiar to what may seem ridiculous initially."
Richard BuchananCreativity and Principles in the Flourishing Enterprise
June 15, 2018
"The goal is not to take notes; the goal is to think effectively, as Andy Matus says."
Jorge ArangoThe Best of Both Worlds: How to Integrate Paper and Digital Notes (1st of 3 seminars)
April 5, 2024
"Competitiveness doesn’t motivate play as much as it used to; companionship and collaboration are more motivating now."
Cheryl PlatzEmbrace Your Fun Factor: Game Development Best Practices for Product Design
January 9, 2026
"If we invest in green technologies today, we can secure a sustainable tomorrow."
Ash BrownSilver Linings: What DesignOps Learned in the Shift to WFH
October 23, 2020
"Dark patterns like Airbnb's price concealment and Twitter's neglect of accessibility were designed decisions, whether designers were involved or not."
Angelos ArnisNavigating the Rapid Shifts in Tech's Turbulent Terrain
October 2, 2023
"If you don’t tell teams what to make, they need a product discovery process to decide what to build."
Jeff GothelfWho does what by how much?
November 20, 2025
"Those who don’t understand history are doomed to repeat it."
Sam ProulxTo Boldly Go: The New Frontiers of Accessibility
September 9, 2022
"What does it mean to be a design ops person? That question matters and we must revisit it often."
Brendan JarvisIt was the Best of Times. It was the Worst of Times.
September 25, 2024
