Production Grade AI Evals by Braintrust.dev

Hosted by Mengying Li

Wed, Nov 5, 2025

5:00 PM UTC (30 minutes)

Virtual (Zoom)

Free to join

278 students

Invite your network

Go deeper with a course

Build with AI: Supercharge Daily Productivity and Master Timeless Principles
Yuzheng Sun, PhD and Yan Wang, PhD
View syllabus

What you'll learn

What evals are

Understand why they're essential for shipping reliable AI products

How to define meaningful quality metrics

Learn to translate “what good looks like” for your AI product into concrete, measurable signals that align your team.

How to build high-signal evals that catch real regressions

Design lightweight but robust evaluation suites that expose true product failures instead of vanity score gains.

When to use offline vs. online evals

Understand the strengths of each and how to combine them into a continuous feedback loop from development to production.

How to integrate evals into your shipping workflow

Set up automated gates and dashboards that let you move fast without breaking quality.

Why this topic matters

Master AI Evals with Braintrust, the industry leader in AI evals. Forget theoretical courses — this is the field-tested playbook for measurement-driven quality. Learn the proven systems to ship safer, faster, and align engineering with true user experience.

You'll learn from

Mengying Li

Mengying Li, Head of Data at Braintrust.dev

Mengying Li is the Head of Data at Braintrust, where she helps scale the business through product-led growth and data-informed decision-making.


Previously, she built and led data and growth teams at MotherDuck, Notion, Meta, and Microsoft, focusing on how data unlocks user engagement, retention, and sustainable growth. Her work sits at the intersection of data, product, and growth, helping teams design evals framework that accelerate learning and impact.

Previously at

Notion
MotherDuck
Microsoft
Meta
a16z

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.