Data Science x AI
Subscribe
Sign in
Home
Notes
Archive
About
What's the Worst Nightmare of an AI Product Builder
The biggest risk facing your AI product
Jan 12
•
Stella Liu
1
1
Latest
Top
Discussions
How We Evaluate Humans vs. How We Evaluate AI
A Lightning Lesson on tests, performance reviews, and AI product metrics
Jan 10
•
Stella Liu
1
3
1
AI Evals: The App-Level vs. Agent-Level “Controversy”
Pick your side?
Jan 5
•
Stella Liu
4
Measuring AI Products: What Truly Matters
Hint: Evals + Analytics
Dec 15, 2025
•
Stella Liu
8
1
Pragmatic AI Evals: Beyond Vendor Promises
What AI Practitioners Need to Know in 2026
Dec 3, 2025
•
Stella Liu
and
Amy Chen
8
2
2
Why Regulated Industries Became the First Real Adopters of AI Evals
Hint: High stakes and real risks
Nov 20, 2025
•
Stella Liu
5
2
1
AI Evals Are Not Unit Tests for AI
Why comparing Evals to unit tests misses the point
Nov 4, 2025
•
Stella Liu
6
1
3
From Evals to Analytics
Understanding What Really Happens After Deployment
Oct 21, 2025
•
Stella Liu
5
See all
Data Science x AI
AI Evals & Analytics.
Subscribe
Recommendations
Design with AI
Xinran Ma
The Cocoons by Stella and Amy
Amy Chen
SeattleDataGuy’s Newsletter
SeattleDataGuy
Almost Magic ✨
Priya Mathew Badger
substacks
The Cocoons
Design with AI
Data Science x AI
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts