Aishwarya Naresh Reganti
Researcher
1
APPEARANCES
1
PODCASTS
012
DEC 30
JAN 6
JAN 13
JAN 20
JAN 27
FEB 3
FEB 10
FEB 17
FEB 24
MAR 3
MAR 10
MAR 17
MAR 24
MAR 31
APR 7
APR 14
APR 21
APR 28
MAY 5
MAY 12
MAY 19
MAY 26
JUN 2
JUN 9
JUN 16
JUN 23
JUN 30
JUL 7
JUL 14
JUL 21
JUL 28
AUG 4
AUG 11
AUG 18
AUG 25
SEP 1
SEP 8
SEP 15
SEP 22
SEP 29
OCT 6
OCT 13
OCT 20
OCT 27
NOV 3
NOV 10
NOV 17
NOV 24
DEC 1
DEC 8
DEC 15
DEC 22
DEC 29
JAN 5
JAN 12
JAN 19
JAN 26
FEB 2
FEB 9
FEB 16
FEB 23
MAR 2
MAR 9
MAR 16
MAR 23
MAR 30
APR 6
APR 13
APR 20
APR 27
MAY 4
MAY 11
MAY 18
MAY 25
JUN 1
JUN 8
JUN 15
JUN 22
JUN 29
JUL 6
JUL 13
JUL 20
JUL 27
AUG 3
AUG 10
AUG 17
AUG 24
AUG 31
SEP 7
SEP 14
SEP 21
Aug 2, 2026
Becoming an AI Engineer in 2026: Interviewing, System Design, Evals | Aishwarya Reganti
23:08
23:17
23:27
23:39
23:47
23:56

Arjay McCandlessHOST
I'm curious what the most common requests are in the systems you keep implementing over and over again.

Aishwarya RegantiGUEST
I mean, at the very bottom, it's mostly trying to understand and codify unstructured data.

Aishwarya RegantiGUEST
And that data could be anything from PDFs or Word documents or any kind of unstructured data.

Aishwarya RegantiGUEST
For instance, customer support is also just understanding a bunch of SOPs and outliers and trying to work with customers.

Aishwarya RegantiGUEST
We had this application, which is underwriter support, right? So much of underwriting is so rigid, and it comes from tons of documentation.

Aishwarya RegantiGUEST
So just having a co-pilot that could help underwriters approve loans or not, depending on a few characteristics, I mean, you know... on whoever is applying for the loan and stuff like that.
6 MINS LATER
S
29:42speaker_2UNKNOWN
Yeah.