
Date
Tuesday, 18 May 2027
Time
14:00–17:00
Duration
3 hours
Level
Intermediate
Price
€160
Capacity
24 seats
Overview
Learn how to evaluate an AI feature beyond a successful demo. In this practical session, you will define useful evaluation criteria, build a repeatable test set and create a simple review loop for quality over time.
What you will learn
Choose evaluation criteria that reflect real user outcomes.
Create a small but useful evaluation dataset.
Compare outputs consistently and document failure patterns.
Turn findings into a practical improvement plan.
Who should attend
Product managers, AI engineers, applied researchers and builders who are responsible for shipping AI-powered features.
What to bring
Bring a laptop, access to a sample project or workflow, and one question you want to solve.
Your host
Maya Bennett is VP of AI at Northstar Labs. She helps product teams build, evaluate and operate dependable AI systems.