What are your first experiences with the new “Interpreter Mode”? It seems to me that this is a very powerful feature. Therefore, I would be interested in what you have used it for so far.
I’ll start with two use cases:
Edit multiple files in the same way in one step. Prompt: Add the code comment “// Written by AI” to all files ending with “Service”. Please search the entire directory structure of the current project for this. Write an executable Python script for this!
Generalize code and extract it into another file: Add two Code snippets as extra context and prompt: “Generalize these two snippets and extract it in a new file with name XXXService”
It’s a big weakness of Cursor, lot of people including me have no idea how most of the features works. Would be nice to have proper tutorial video or at least some documentation.
Sure, I’d be glad to point you to the documentation, but first, could you clarify which documentation you’re referring to? This will help me provide you with the most accurate information and direction.
I"m using interpreter to process all kinds of data locally, such as CSVs, spreadsheets, etc. It uses Python, has access to basically the whole file-system and can execute any operation, so I usually use “auto-execute” (I’m inside a virtual machine though, so it’s relatively safe). It helps a lot and you don’t have to upload any data anywhere, like with ChatGPT’s Interpreter.
I’ve tried using it for batch editing codebase, but found it not as strong there, as it sometimes misedits files or saves to the wrong file for some reason. However, for simple batch edits in the codebase it usually works well.
I use it to build and actually soon ship a finished digital product, without knowing how to code (yes it is not a complex product)
But my coworkers don’t get bothered by me asking for help all the time when I ise this interpreter mode