{"blocks": [{"key": "0a20fae9", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "58c2a14b", "text": "Meta is evaluating a new social feature called Circle (similar to Facebook Groups) and wants to decide how to measure and optimize it.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "3cf001ef", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "a6441c21", "text": "What metrics would you track to measure the success of Circle, given it is the only feature on the platform and guardrail metrics/cannibalization are irrelevant? Using only retrospective data, how would you decide whether Circle should be optimized for small groups (≈5–6 members) or large groups (tens to hundreds)? You are shown three time-series plots of total comments per total posts for three different products with different user bases. Can these lines be directly compared? Explain.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "62ce4792", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "a7373ed6", "text": "Select a north-star metric; segment by cohort size; normalize metrics before comparison.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}