2 min lesson
Context hygiene: feed the model less, more often
Put yourself in this case: "You've been working one long Cursor chat all afternoon and the answers are getting vaguer. The context icon reads about 60% full. What's the right move?" Give the clearest next step.
Step 1 of 3
Context hygiene: feed the model less, more oftenthe discipline that keeps answers sharp
Most frontier models carry roughly a 200,000-token context window, and a token is about 75% of a word. Cursor shows how full it is (you'll see something like "160k / 176k" on the model). When it fills, Cursor auto-summarizes to compress it, or you can run /summarize yourself. The catch a PM should know: degradation can start well before the hard limit - past roughly 50-60% usage, some models get noticeably worse.
Interactive widget. Tab through its controls; the result updates in the panel below as you change them.
Performance can sag past ~50-60% usage, not just at the hard limit - summarize or fork before then.