← Evals & Launch Decisions / 34
hardNewSpotifyMeta

Our assistant now personalises answers using each user's history. How do you evaluate quality when there's no single right answer?

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

Compare the same request with and without the profile, judged by people who see the profile, and test the three failures users notice: ignoring a stated preference, using a stale one and over-personalising.

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

Compare the same request with and without the profile, judged by people who see the profile, and test the three failures users notice: ignoring a stated preference, using a stale one and over-personalising.

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
NOTES & DISCUSSION · 0

No comments yet. How would you have answered?