66% system prompt reduction enabled by model capability gains
As models improved, explicit prohibitions and prescriptive instructions became unnecessary; Cursor trimmed approximately 66% of its system prompt by relying on model compliance with concise tool behavior definitions.
Evidencia a favor
Improved token efficiency for longer agent runs · Cursor
Extracto original
This was true across model families, allowing us to trim roughly 66% of our system prompt.
Contexto
As models improved, much of that direction became unnecessary. Instead of long lists of "DO NOT do this," "You must," or "Important" instructions, we could simply define how a tool behaves and models would generally comply.