Session

Before you UPDATE with an LLM

Imagine a situation where you’re the DBA on staff for a multinational company, and it’s been decided (finally!!) that it’s time to clean up all of the messy and bad data that has accumulated over the decades and has been compounded by acquisitions, aborted data cleanup initiatives, and just lack of motivation.

The CIO approaches you and says - let’s just let AI fix it for us. Just upload all the data into your favorite AI and it will be clean before lunch. Being an experienced DBA, you know the following:

1) The AI might not be the most accurate way to accomplish this
2) It’s going to add in additional expense for the massive number of tokens
3) There are other issues like data sovereignty and privacy that may come to play

Let’s compare and contrast real numbers from having DBAs and AIs work together to do a better job, ideally save money, and accomplish more in the mean time!

We will be providing real test results from expert DBAs using their own home-grown techniques to refine the data first, the DBA attempts AFTER the AI has had the first crack at the data, and the actual cost in labor and tokens in order to accomplish this task.

Michael Wall

Architect/DBA at 3Cloud Consulting

Vancouver, Washington, United States

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top