AI Evals for Product Managers
Catalina Turlea
Co-founder @ Lovelaice,
Madalina Turlea
Founder @Lovelaice | 10 years in FinTech
Take the lead of building AI features and evaluating them
Most product managers shipping AI features today are doing some version of the same thing: writing a prompt, testing it on a few examples that feel representative, and hoping it holds up in production. Nobody calls it a "vibe check", but that's what it is.
PMs have never been given a real method for this. AI evaluation has lived in engineering territory for years, built by developers for developers, wrapped in technical jargon that signals "this isn't for you."
That's the wrong setup. The people best positioned to evaluate AI features aren't the ones who built the model. They're the ones who understand what "good" looks like for the user and that's you.
In one day, you'll go from gut-feel checks to structured evaluations that give you real data: which model, which prompt version, which configuration actually performs for your use case. You'll leave with a repeatable method and a way to talk about AI quality that doesn't require an engineering translation layer.
If you've ever shipped an AI feature and genuinely didn't know if it was working, this workshop is for you.
Workshop agenda
- 8:00AM EDT
Introduction into AI Feature Building for PMs
Map your use case to a real product opportunity, defining what "good" looks like before a single prompt is written. You'll leave this session with a scoped feature, a clear success criteria, and the
- 8:30AM EDT
Running first experiments
Put your feature to the test using a structured evaluation framework. You'll compare model outputs against your criteria, spot failure patterns, and make your first data-backed decisions.
- 9:00AM EDT
Writing first Evals for your AI Feature
Turn what you learned from the experiment into a repeatable evaluation setup. Write your own eval framework
Who this workshop is for
The PM who owns an AI feature but not the process around it
The PM about to pitch an AI feature internally
The product lead responsible for a whole team's AI output
What's included
Live sessions
Learn directly from Catalina Turlea & Madalina Turlea in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
$200
USD