Hello Cursor.AI team,
I’m a regular user of your product and have found it to be incredibly helpful in my workflow. However, I would like to request a new feature that would enhance the user experience.
I’ve noticed that sometimes Cursor modifies parts of the code that are unrelated to the task at hand, even when those sections should remain unchanged. This can be problematic, especially when working with specific LLM models. To address this, I propose adding a feature that allows users to include hard-coded instructions within the code, in the form of comments. These comments would indicate to Cursor that the enclosed code should not be altered under any circumstances.
For example, when defining an LLM model as a variable, users could specify that this part of the code is off-limits for modifications. This would ensure that crucial sections remain intact, preventing unnecessary changes and streamlining the coding process.
Thank you for considering this suggestion. I believe it would greatly benefit Cursor.AI users.
Best regards