The Only 3 AI Tools I Actually Use for Data Work

Hey guys,

Every day it seems like there’s a new fancy AI tool that comes out and it’s hard to keep track of which ones are actually important and which ones you can forget about.

As someone who works in data this is even more prevalent because most of the AI tools aren’t built for data scientists, analysts, or engineers.

Over the past couple of years I’ve been trying out and using a lot of them and trying to figure out which ones are actually important and can help with productivity, coding, and ideation.

So let’s go over the three that I use that I believe are essential for working in data.

---

1. ChatGPT

ChatGPT is, without a doubt, the tool I use the most.

It’s completely replaced Google for me when I’m looking to learn something new, debug code, or explore ideas.

Since its release in 2022, I’ve used it to:

• Speed up code development

• Generate ideas and outlines

• Research new frameworks and tools

• Learn unfamiliar concepts quickly

As the underlying models have improved, so has ChatGPT, especially when it comes to generating code.

Whenever I need to build something new (like a chatbot, infrastructure automation, or a custom data pipeline), it helps me move faster from idea to execution.

Although it still definitely isn’t a perfect solution, just like many of these ai tools.

When it comes to business logic or domain-specific edge cases, I still rely on my own knowledge.

Which is why I still strongly believe in learning to code and advocating for people to learn to code.

But in terms of accelerating learning and productivity, it’s been a 10x multiplier.

---

2. Cursor

Cursor took some time for me to find an actual use case.

Since I am doing 99% data work in my day job and in online teaching, it wasn’t great for heavy Python workflows or Jupyter Notebooks, which made it hard to integrate into my daily work.

But recently, they added proper support for notebooks and now I’m never going back haha.

Having an AI chat assistant directly inside the notebook interface has been a game changer.

It helps me debug, test ideas, and refactor code much faster than before.

At this point, I don’t see myself going back to the traditional Jupyter environment in the browser.

---

3. DataGrip with GitHub Copilot

Finding a solid AI tool for SQL and databases has been a struggle. and I’ve mainly felt that most of what’s out there just isn’t that good.

I’ve been using JetBrains DataGrip with GitHub Copilot integrated and it’s made working on databases and writing SQL a lot better.

It’s not perfect, but it’s better than anything else I’ve tried.

Copilot does a surprisingly good job of generating SQL snippets, explaining complex queries, and helping me write faster in general.

If you do a lot of SQL work and haven’t found a solid assistant yet, this combo is worth trying.

So give these a try, and let me know if there’s any AI tools that you use personally that are essential to your workflow.

Until next time,

McKay

---

ps. I’ve been thinking about using this newsletter to go more in depth with topics and have more advanced technical discussions on AI, building with AI, and more.

Is that something you would be interested in or just keep it beginner friendly?

Thanks again for reading and for the support!