Rosenverse

Log in or create a free Rosenverse account to watch this video.

Log in Create free account

100s 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

Wednesday, October 8, 2025 • Rosenfeld Community

This video is featured in the Evals + Claude playlist.

Share the love for this talk
Hands-on AI #1: Let’s write your first AI eval
Speakers: Peter Van Dijck
Link:

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."

Ask the Rosenbot
Frank Duran
Partnership Playbook: Lessons Learned in Effective Partnership
2024 • Enterprise Experience 2020
Gold
Theresa Slate
Why Changing Hearts & Minds Doesn’t Work When Promoting DE&I Efforts, but Checklists Do
2023 • DesignOps Summit 2023
Gold
Savina Hawkins
Harnessing AI in UXR: Practical Strategies for Positive Impact
2024 • Advancing Research 2024
Gold
Sydney Lawson
Anatomy of a Strong User Panel
2026 • Advancing Research 2026
Gold
Mila Kuznetsova
How Lessons Learned from Our Youngest Users Can Help Us Evolve our Practices
2022 • Advancing Research 2022
Gold
Bria Alexander
Opening Remarks
2023 • Advancing Research 2023
Gold
Dr. Jamika D. Burge
A Genuine Conversation about the Future of UX Research
2024 • Advancing Research Community
Peter Van Dijck
Coffee with Lou #4: Taking a Peek Under the Rosenbot's Hood
2024 • Rosenfeld Community
Jack Moffett
SAFe or Sorry?
2019 • Enterprise Community
Cheryl Platz
Collaborative Creativity through Improv
2018 • DesignOps Summit 2018
Gold
Kate Towsey
ResearchOps AMA with Kate Towsey & Jake Burghardt
2025 • Advancing Research Community
Bud Caddell
DesignOps Community Sensing Session
2021 • DesignOps Community
Dane DeSutter
Beyond the Console: The rise of the Gamer Experience and how gaming will impact UX Research across industries
2024 • QuantQual Interest Group
Dorelle Rabinowitz
The Magic Word is Trust
2018 • Enterprise Experience 2018
Gold
Paul Pangaro, PhD
Systems Disciplines: Table Stakes for 21st Century Organizations
2023 • Enterprise UX 2023
Gold
Ashley Cortez
Shifting Toward Community-Led Innovation in Local Government
2021 • Civic Design 2021
Gold

More Videos

Leisa Reichelt

"Empathy walls emerged at DTA because teams needed a visceral way to bring stories back from the field."

Leisa Reichelt

Opening Keynote: Operating in Context

November 7, 2018

Cennydd Bowles

"Support structures for switching from design to academia are sparse; you mostly have to figure it out yourself."

Cennydd Bowles

Exit Interview #2: Rediscovering the ethical heart of design

November 6, 2025

Andrew Michael

"Embedded squads build domain expertise but risk losing knowledge if someone leaves, while centralized teams help reduce duplicated effort."

Andrew Michael

Building a Product Insights Team

March 10, 2022

Veevi Rosenstein

"Having a back office support in place made it much easier to convince new researchers to join the team."

Veevi Rosenstein

Building for Scale: Creating the Zendesk UX Research Practice

January 8, 2024

Megan Campos

"Age carries with it obvious visible differences and lived experience, while race often involves less visible but equally impactful structures."

Megan Campos

What Did I Miss? The Hidden Costs of Deprioritizing Diversity in User Research

March 12, 2021

Aras Bilgen

"The app reads the question and prepares tutoring material, then helps solve it step by step or through chat if further questions remain."

Aras Bilgen

Who does the math: A designer’s journey in building an AI-based tutoring app

June 10, 2025

Ron Bronson

"If you do enough research, you might find 20% of your users are edge cases, so maybe you’re not building for the right people."

Ron Bronson

Design, Consequences & Everyday Life

November 18, 2022

Tina Weisser

"The chaos of undocumented processes makes it hard to build useful AI workflows; mapping and blueprinting help."

Tina Weisser

When AI Agents Meet Reality. Service Design Lessons from a Pilot

February 26, 2026

Dr Chloe Sharp

"As the product journey progressed, research cadence got faster with prototypes and quicker feedback loops."

Dr Chloe Sharp

Using Evidence and Collaboration for Setting and Defending Priorities

November 29, 2023