Skip to main content
Shreya Shankar

Shreya Shankar

Search complete. 2 mentions across 2 episodes found for "Shreya Shankar".

Nov 16, 2026

speaker_0NARRATOR
3:47
A good eval starts with failures you have seen.
speaker_0NARRATOR
3:50
Two practitioners, Hamal Hussain and Shreya Shankar, say the most important activity in evals is going through real outputs and sorting the failures.
speaker_0NARRATOR
3:59
Each check is a yes or no question.
speaker_0NARRATOR
4:02
For example, does the first paragraph tell the client what we need from them? Anyone checking will give the same answer.
Tristan HandyHOST
0:41
Welcome to the analytics engineering podcast, featuring conversations with practitioners inventing the future of analytics engineering.
Tristan HandyHOST
0:52
In this episode, I'm speaking with Shreya Shankar, longtime data practitioner and soon to be faculty at Carnegie Mellon, collaborating with the great Andy Pavlo in the database group.
Tristan HandyHOST
1:03
Shreya has spent the past few years conducting research at the intersection of databases and large language models.
Tristan HandyHOST
1:10
And she's gone the deepest of anyone I've personally spoken to on how these two areas come together.

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.