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
"Trust with your team needs to be established and continuously nurtured because tough situations arise quickly."
Anna Avrekh Dr. John Pagonis Klara Pelcl Sina SchreiberExpert Panel: Leading in and with Research
March 10, 2022
"If we just decide to ignore demographics we're missing huge swaths of the participant experience and an opportunity to better serve our users."
Megan CamposWhat Did I Miss? The Hidden Costs of Deprioritizing Diversity in User Research
March 12, 2021
"If a person has a human moment that’s grounds for dismissal, it ends up muting my personality."
Kat VellosOpener: The Other L Word
January 8, 2024
"The best people in a community experience 90% awesome when the reality is 10%."
Adrian HowardSturgeon’s Biases
September 25, 2024
"Expectation describes how things ought to be and reinforces the distinction between the present and what is not yet here."
Nicole AleongFuture Orientations to Everyday Life: Futures Anthropology as a Methodology
March 26, 2024
"I’ve done the headscarf when recruiting door to door at the mosques of East London."
Tamara HaleWar Stories LIVE! Tamara Hale
March 30, 2020
"The pressure to produce insights quickly defines many organizations shaped by 'move fast and break things' culture."
Rachael Dietkus, LCSWThe power to heal and harm
March 13, 2025
"Historians say the past doesn’t repeat itself, it rhymes."
Steve PortigalLooking Back…to Look Ahead
March 26, 2024
"Nearly three quarters of those surviving violent trauma report alcohol use disorders, which can lead to thoughts of suicide."
Megan Nipe Lyndsay BoothHuman-Centered Design for Engagement: Maturing from Newsletterville to Personalized, One-to-One Messaging
December 8, 2021
