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 #2: Understanding evals: LLM as a Judge
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
"If you value innovation and design, then you're investing in creativity."
Dr. Karl JeffriesThe Science of Creativity for DesignOps
January 8, 2024
"When we showed the Iceland Ministry of Foreign Affairs their portfolio, the Foreign Minister said, we have to pivot our innovation investments to early-stage catalytic innovations."
Milan Guenther Benjamin KumpfThe $212 billion ‘so what?’: unlocking impact in development cooperation
November 20, 2025
"Research repositories aren’t single sources of truth anymore; data and insights live in hundreds of different apps across companies."
Ben Davies Matt Duignan Andrew Michael Dr. Emily DiLeoExpert Panel: The Principles of Research Repository Design
March 11, 2022
"We’re showing people how to collaborate like crazy and how to fail gracefully."
Phil GilbertA Consistent Culture of Design
May 14, 2015
"Building more ethical, responsible, and humanistic forms of technologies requires diverse and interdisciplinary conversations."
Prayag Narula Rida QadriHCI 2.0: Humanity Deserves the Attention that UX Research has to Offer
March 28, 2023
"Research ops was actually there before research at TravelPerk, supporting designers first."
Ned Dwyer Emily Stewart James WallisThe Intersection of Design and ResearchOps
September 24, 2024
"We are the shopkeepers of today; it just looks a little bit different."
Erin WeigelReal-world lessons to improve your conversion rates
June 26, 2024
"You cannot design for the middle; instead, you must create experiences that are customizable and adaptable."
Samuel ProulxFrom Standards to Innovation: Why Inclusive Design Wins
November 19, 2025
"Mastery is a core human motivator; people want to understand and feel competent in what they do."
Cheryl PlatzEmbrace Your Fun Factor: Game Development Best Practices for Product Design
January 9, 2026
Latest Books All books
Dig deeper with the Rosenbot
What steps help build trust and healing in communities affected by historical traumas during engagement?
How should communication style change when working with contractors compared to corporate colleagues?
What role does cultural storytelling play in improving research understanding and connection?