[ETR #35] AI Can Train You In DE


Extract. Transform. Read.

A newsletter from Pipeline

Hi past, present or future data professional!

Software engineers can package anything— including buzzwords. “Learn new, industry-relevant skills” was compressed to “upskilling.”

And while I’m a proponent of continuous learning, especially when it helps you avoid stagnation, at the end of the day, upskilling is a lot of work. Without proper structure and no mandate from a school or employer, it’s difficult to remain engaged, no matter how interesting the content.

My Udemy cart with 5 unfinished courses can attest to that.

So when I wanted to brush up on the ever-relevant PySpark, I booked some time with Professor LLM; LLMs like Google’s Gemini (my choice to be compatible with my GCP tech stack) make incredible teachers because, like a real tutor, they can engage in a dialogue and adjust to your learning style on the fly.

As a former tutor, I appreciate that it explains concepts as it provides results. This is the educational equivalent of “showing your work.”

To get the most out of your chat bot study sesh, I recommend:

  • Providing experience level context and desired trajectory: “I have 2 years’ experience with SQL but I’d like to learn more about CTEs as they relate to query optimization
  • Prompting the LLM to explain concepts as they relate to a specific role: “Show me examples of how a data engineer might use this skill/tool to build a data pipeline”
  • Repeating subject matter for confirmation: “Let me make sure I have this right, certain Python versions are no longer compatible with Pandas?”
  • Code correction/optimization: “How might I make this code more concise?”
  • Demonstrating errors: “What are the common errors associated with this method? How might I troubleshoot? How might I handle the errors?“

Lost in the AI hype is the power of being able to streamline simple tasks. I did this recently by using function calls to automate the conversion of Google Docs to markdown files I can render as blog posts.

Answering a string of questions as a “teacher” isn’t as revolutionary as an AI creating “original” movies or podcasts.

But by optimizing your learning, you’re creating an abundance of something far more valuable: Time.

Thanks for ingesting,

-Zach Quinn

Extract. Transform. Read.

Reaching 20k+ readers on Medium and over 3k learners by email, I draw on my 4 years of experience as a Senior Data Engineer to demystify data science, cloud and programming concepts while sharing job hunt strategies so you can land and excel in data-driven roles. Subscribe for 500 words of actionable advice every Thursday.

Read more from Extract. Transform. Read.

Hi fellow data professional! SQL Lite, the database you most likely learned SQL on, is built atop 100k lines of source code. Sound like a lot? Compare that to Chromium, the engine for Google Chrome, which boasts 30+ million lines of code under the hood. Shortly after acquiring Twitter/X, the world's first trillionaire, Elon Musk, famously asked engineers to tell him how many lines of code they wrote per day, igniting a debate among engineers throughout the software and data domains. When I...

Hi fellow data professional! If you read my note on Tuesday you’ll know I’m coming off of the data engineering week from hell that seeped into my personal life, and delayed the launch of something cool I was planning to share with you; if you want to know more about that, scroll to the end of this message. Last week a flagship data source had a major problem and since it’s within my ownership area, I was the one with the knowledge and responsibility to fix it. I wanted to share the experience...

Hi fellow data professional! Hardly a work day goes by without receiving a request from a data analyst. They range from the mundane “Can you add this column?” to the occasional emergency “The data didn’t load all weekend and the leadership call starts in 15 minutes!” At the end of a jam-packed week I received an unusual request: Help with a Python script. My teammate wanted to know: Best practices How to commit to GitHub What the best way to deploy is They admitted the task was simple,...