Chat with your data in dozens of human languages. I am still in college learning new things. But I try to be helpful. I did finish my required reading: thousands of books, millions of code repositories, and billions of web pages.


  • Start small. Gradually add complexity. First, try simple requests such as distributions, basic plots, or simple models. Then customize it or add variables.
  • Releases as a prototype, it is still being developed. Please send us your valuable feedback (lower left).
  • It can take a few tries to get it correct. If it still does not work, rephrase your request. Also, increase the "Temperature" setting will make the AI more aggressive in seeking alternative solutions.
  • Prepare and clean your data in Excel first! RTutor can only analyze traditional statistics data, where rows are observations and columns are variables.
  • Once uploaded, your data is automatically loaded into RTutor as a data frame called df. Check if the data types of the columns are correct. Change if needed, especially when numbers are used to code for categories. Data types make a big difference in analysis and plots!
  • Before sending your request to OpenAI, we add "Generate R code" before it, and append something like "Use the df data frame. Note that hwy is numeric" afterward. If you are not using any data (plot a function or simulations), choose "No data" from the Data dropdown.
  • Your data is not sent to the AI. To ask generic questions without mentioning column names, briefly describe your data, especially the relevant columns, just like emailing a statistician who knows nothing about your data.
  • Each chunk of code is run independently using your uploaded data. If you want to build upon the current code, select the "Continue from this chunk" checkbox. Your current R code will be inserted before your next chunk and get executed. This is especially important for data wrangling when you remove rows, add columns, or log-transform. You can go back to any previous chunks and continue from there.