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.
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 second talk in the series, Peter Van Dijck of the helpful intelligence company will show you how to create an eval for an AI product using an LLM as a judge (when we use a Large Language Model to evaluate the output of another Large Language Model). We’ll have a look at how that works, but also dig into why this even works. Are we creating problems for ourselves when we let an LLM judge itself? This talk is hands on; and there will be plenty of time for questions. You will go away understanding when and how to use LLM as a judge, and build 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 are a foundational feedback loop defining what 'good' means for AI products, helping to measure and improve systems continuously.
-
•
Evaluating fuzzy, subjective AI outputs requires innovative approaches such as using LLMs as judges to score results.
-
•
Binary (yes/no) scoring is more reliable than rating scales with ranges because LLMs lack internal memory and consistency.
-
•
Starting evals early (week one of a project) drastically improves AI product outcomes, but many teams delay due to perceived complexity.
-
•
High-risk or important tasks should be prioritized for evals instead of attempting broad coverage.
-
•
Assigning a dedicated owner or 'benevolent dictator' for evals who works closely with domain experts accelerates feedback and quality.
-
•
Creating a written constitution of principles helps concretize AI behavior goals and guides prompt and model training.
-
•
Most current eval tooling is too technical, slowing iteration cycles and making expert involvement inefficient.
-
•
Custom feedback interfaces tailored to expert users significantly speed up evaluating AI outputs in domains like healthcare and law.
-
•
Diverse perspectives from UX, product, strategy, and domain experts are critical in defining and refining what 'good' means in AI systems.
Notable Quotes
"Evals are everywhere, right? Everybody's talking about evals. It is like one of the key things in developing useful AI products."
"You want to ask an LLM to evaluate the fuzzy stuff because there’s no black and white output."
"LLMs don’t have memory, so rating on a scale from one to five is pretty random. Better to have yes or no answers."
"One of the biggest problems in AI building is evolving your prompts and having a fast feedback loop."
"By starting to categorize risk in detail, you naturally lead to better prompts and better evals."
"A constitution is a very good exercise: write down your system’s principles and values to help guide its behavior."
"Use custom systems for experts to quickly review and rate outputs, making feedback cycles much faster."
"Evals define a shared definition of good with tests to measure it, and that is the secret sauce for building great AI products."
"Model companies are students in a classroom wanting good points—they’re happy to run external expert evals to improve."
"The more I work with evals, the more I think UX and product people need to be involved because of the need for diverse perspectives."
Or choose a question:
More Videos
"By default, you’re getting I am very confident of my answers."
Trisha Causley[Demo] Complexity in disguise: Crafting experiences for generative AI features
June 5, 2024
"Research ops is like the most punk thing you can do in the experience design space."
Kate TowseyAsk Me Anything (AMA) with Kate Towsey
April 2, 2025
"When design ops comes in hot, it means honest, orchestrated, and timely."
Briana Thomas Christina RodriguezWhen Design Ops Comes in H.O.T. : A Tale of a Transformed Design Org
September 30, 2021
"Optimal design leadership looked like a CEO who promoted design as strategy and a chief design officer with the ear of the CEO."
Brianna SylverLead With Purpose
March 31, 2020
"We enable PMs and designers to conduct research rigorously because they are already in contact with customers daily."
Anna Poznyakov Richa PrajapatiGet The Most Out Of Stakeholder Collaboration—and Maximize Your Research Impact
March 12, 2021
"Engaging influencers early helped them appreciate being included sooner than later, which improved the project."
Frank DuranPartnership Playbook: Lessons Learned in Effective Partnership
January 8, 2024
"If you design for everyone, no one is satisfied — start with specific solutions then generalize."
Craig VillamorResilient Enterprise Design
June 8, 2017
"I’m not looking for cookie cutter candidates; I want to hear someone who’s taken the less traveled, maybe more challenging route."
Rachel Radway Katie Bingham Joe WiertelThe Many Paths Of Design Operations
September 8, 2022
"Product managers are responsible for value – making sure something valuable is being created that meets real needs."
Christian CrumlishAMA with Christian Crumlish, author of Product Management for UX People
March 24, 2022
