Test Cursor on a real data science task
A data scientist graded Cursor on a Python football project and found it strongest for quick prototypes, but weak on pandas, cleaning, and scraping.
- What they did
- Mike Woodward tried Cursor, using Claude underneath, on a live Python data science project built around English football data. He had it generate code, then checked the results and repaired parts by hand. For one pandas question about clubs that appeared only at home or only away, he ended up writing the query himself.
- How it went
- He scored it A for completion, comments, documentation, and prototyping. It got C for pandas, cleaning, and code generation, and D for scraping and getting started. Streamlit apps were assembled quickly, but technical work still needed close review.
- Tips
- Use it for early drafts and app mockups, but expect to verify anything involving data wrangling or scraping. Keep backups, because Cursor removed some data files during GitHub work and the free tier was used up quickly, making a paid plan necessary for testing.
Try it yourself with Cursor
I’m working in [folder path] on a [project type] about [goal]. Help me tackle these tasks one by one: [task 1], [task 2], [task 3]. For each task, explain your approach, show the code or changes you would make, and say what I should double-check manually. Before you do anything that could overwrite, delete, send, submit, or charge anything, pause and ask for my approval. End with a short score for each task and a note on where the solution may be fragile.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Build a linked research wiki from source files
They used Cursor to turn papers and articles into a browsable markdown wiki with summaries, links, and an index inside Obsidian.
Draft an academic paper in Markdown with Cursor
A writer used Cursor to help draft and revise papers in Markdown while pulling citations from Zotero and a BibTeX library.
Let Cursor audit and summarize an Obsidian vault
Beatriz used Cursor to inspect her Obsidian vault, flag structure issues, answer note questions, and log what other sessions changed.
Build a dashboard from a semantic data layer
Use a coding agent with Graphene to define metrics, query your warehouse, and publish a report with charts and screenshots.
Have a coding agent check papers before each experiment
A Claude Code agent with paper search found useful ideas that a plain run missed while tuning a small language model.
Use AI to map a thesis literature review
They used ChatGPT to summarize papers and sketch the review, then switched to a source-first tool to cut citation risk.