36Design a background coding agent that opens pull requests across 2,000 repositories. Which work should it get?▼expertNewSpotifyGoogleMicrosoft◆ premiumTokens cost under a dollar per run; reviewer time costs thirty times that. Choose the task classes, the permissions and the gates that decide what a human ever sees.Practise this question →Read answer →
40We turned on an AI code reviewer that comments on every pull request. How do you tell whether it catches real problems or just adds noise?▼hardNewAtlassianGoogleMicrosoft◆ premiumPublished systems measure whether comments lead to code changes, aim for a precision target and filter non-actionable comments. Compare against human comments, seed known bugs for recall and run a randomised rollout.Practise this question →Read answer →
39With AI, developers merge far more pull requests, but releases and incidents haven't improved. What do you measure and fund?▼hardNewAtlassianGoogleMicrosoft◆ premiumGenerating more code moves the bottleneck to review, testing and release. Switch the scorecard to delivery metrics and put the next budget into review and testing capacity.Practise this question →Read answer →
27A coding agent opened a 40-file pull request for your feature. As the PM, how do you review it before it ships?▼mediumNewCursorAtlassianStripe◆ premiumA PM does not review code line by line. The scored answer shows what a PM checks in an agent's pull request, what engineering checks, and when a 40-file change should be sent back.Practise this question →Read answer →