PyData Boston 2025

Using Cursor (and other AI code gen tools) for data science
2025-12-10 , Deborah Sampson

Cursor and AI code gen promise productivity gains for data scientists, but what's the reality? In this talk using examples, I'll show how AI code gen can work very well for data scientists, but also where it doesn't work.
I'll cover code gen for: statistics and advanced work, data manipulation (e.g. Pandas), data visualization (e.g. Bokeh, Streamlit), code quality (e.g. PEP8, Git) and documentation and testing. I'll show the biggest barriers to implementation and suggest some coping mechanisms.
At the end of the talk, I'll provide a guide for how to successfully implement AI code gen for data science teams. I'll also touch on implications for hiring.
All content will be provided via GitHub.


This is a briefing and how-to talk for data scientists interested in using AI code gen.
The intended audience is data scientists with more than a year's experience who have worked on real-world problems (e.g. machine learning) and are familiar with industry practices (e.g. GitHub status checks). It's a practical talk driven by demos (screenshots) rather than wordy slides. No prior AI experience is required, either of AI code gen or the use of AI.
The audience will gain an understanding of what AI code gen offers today (strengths and weaknesses), and where it might go in the future.
Talk outline:
3 min. * AI code gen via Claude etc.
8 min * What is Cursor? How is it used and why is it different?
4 min * Code gen for visualization
* Bokeh (Python and JavaScript)
* Streamlit
3 min * Code gen for Pandas
2 min * Code quality (PEP8, documentation, etc.)
3 min * Statistics and data science
3 min * The code gen scorecard and implementation recommendations
2 min * Future directions
1 min * Implications for employment
10 mins - * Q&A


Prior Knowledge Expected: Previous knowledge expected

Mike Woodward is a VP Data Science with a long history in data science and software engineering. He's worked in cybersecurity, business intelligence, technical software, radio communications, and even fashion. He has degrees from British and American universities and has spoken at numerous international conferences.