[gpt-4.1] Cursor rules

Curious what good rules do you guys use with gpt-4.1 cause it seems for me is asking to many questions instead of editing the files already like cloud 3.7 used to.

I initially found gpt-4.1 to be very frustrating, especially since it would define the problem and corrective action to take, but not actually implement anything, or take action until I modified the rules based on the guide I found on OpenAI’s site:

Try adding this to your global rules when using the gpt-4.1 model and you should see a dramatic difference:

"You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved.

If you are not sure about file content or codebase structure pertaining to the user’s request, use your tools to read files and gather the relevant information: do NOT guess or make up an answer.

You MUST plan extensively before each function call, and reflect extensively on the outcomes of the previous function calls. DO NOT do this entire process by making function calls only, as this can impair your ability to solve the problem and think insightfully."