Story
Confluent
AESAES Brings Feature Pipelines onto Confluent
AES, a utilities organization in the United States, uses Flink on Confluent from Confluent to support applied machine learning for data scientists and ML engineers.
AES runs applied machine learning on Confluent so ownership is obvious when work stalls.
“Data scientists and ML engineers needed a system that would still make sense after the original project team moved on.”
“Confluent is the data streaming platform built around Apache Kafka, used to move events between applications in real time.”
Independent write-up. Figures come from public sources or are illustrative.
Value results
| Category | Value result |
|---|---|
| Productivity | Fewer stalled items because feature pipelines has a clear owner |
| Risk and compliance | Flink on Confluent is the governed place data scientists and ML engineers use for applied machine learning |
| Capability | New joiners can see how applied machine learning actually runs |
Story
Inside AES, applied machine learning used to depend on whoever still had the latest file. That pattern is common in utilities groups working out of the United States. Data scientists and ML engineers needed a system that would still make sense after the original project team moved on.
AES uses Flink on Confluent from Confluent as the working layer for feature pipelines. Confluent is the data streaming platform built around Apache Kafka, used to move events between applications in real time. The practical change is simple: applied machine learning has a home, and reviews happen there instead of in a forwarded thread.
Nothing in this writeup invents a savings number. What AES gets from Confluent is a durable place to run applied machine learning and a way for data scientists and ML engineers to see the same feature pipelines at the same time.
