How many teams to detect a 2% lift when you randomize by team?
Power & sample sizeHardProblem. Figma's real product wins are small. A share modal redesign moved invites by about 2%. Your PM wants to know whether a similar change to the upgrade flow can be tested, and how long it would take. Viewer-to-editor conversion is around 2%. Size the test.
Before you reveal: say your answer out loud, as if you were in the real interview — get your reasoning across clearly first. There is no single correct answer: reading what the interviewer is really after and defending your own thinking is what makes an answer strong.