hardNewGoogleMicrosoftMeta

Our proactive AI gets more notification clicks but users mute it. When should it interrupt them?

Try it in the practice workspaceDraft your answer before comparing it with the rubric.

Design an interruption policy from urgency and consequence, then measure useful action and attention cost beyond clicks.

Updated Oct 2026 · Original practice questions with worked answers and teaching rubrics. Our editorial policy explains the sources, review process and limits.

Case briefRead the inputs, then make your call

A work assistant is testing a more aggressive notification policy. The weekly randomized test is fictional.

Scenario inputs
Assignment	1,000 eligible users in each arm.
Baseline	2,000 notifications; 200 clicks; 140 useful completed actions; 20 users mute.
Candidate	5,000 notifications; 350 clicks; 150 useful completed actions; 80 users mute.

Your task. Choose an interruption policy, interpret outcomes with their denominators and define conditions for expansion.

Design an interruption policy from urgency and consequence, then measure useful action and attention cost beyond clicks.

This reference answer is in Premium. Free signup opens other answers.

9 answers per topic instead of 5, and your progress kept · no cardor unlock all 420 remaining answers

UP NEXT ON YOUR JOURNEY

Next in this trackThe Empty Prompt Box Problem Next in this trackWhen Remembering Feels Like Surveillance Next in this trackAccessible AI Chat for Screen Readers

NOTES & DISCUSSION · 0

No comments yet. How would you have answered?