{"blocks": [{"key": "234b6b51", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "c60f62a7", "text": "Ads team is replacing a rule-based ad ranking with a new recommendation system; UI and auction rules stay the same.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "fff271a7", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "0bcf7b95", "text": "Which primary and guardrail metrics would you track for this launch and why? How would you design the A/B test so control and treatment populations are truly comparable? Write the formulas you would use to estimate required sample size and test duration. If treatment CTR rises 5%, will advertisers necessarily spend more? Explain the causal path and additional analyses you would run. Below is a chart where treatment CTR is already higher than control during the pre-launch period. What is wrong with this picture and how would you fix the visualization? How would you summarize results, next steps, and risks for senior leadership?", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "cb7f29a1", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "b3f92993", "text": "Think metric hierarchy, randomization, statistical power, business incentives, visualization best-practices, and executive storytelling.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}