Ai Coding And Product Systems easy
Your AI code review bot posts comments on pull requests, but developers have started ignoring it. An audit shows about 40% of its comments are wrong or irrelevant. What is the best first step?
- A Increase the number of comments per PR so real issues are more likely to be caught overall.
- B Switch to a larger model and keep every comment, since a bigger model will be right more often.
- C Post comments as blocking checks so developers are forced to read and respond to every one.
- D Raise the confidence threshold and drop low-precision categories, accepting some missed issues.
Answer: D. Raise the confidence threshold and drop low-precision categories, accepting some missed issues.
Review tools live or die on **false positive rate**: once more than about 1 in 3 comments is wrong, developers ignore all of them. Trading some recall for precision restores trust in the comments that remain. A larger model (B) may help a little, but it does not change a design that posts every low-confidence finding.
One system design question a day, with spaced repetition so the ones you miss come back.
Get the appRelated questions
- Your assistant uses a classifier to route queries to a small or large model, which saves 60% of GPU spend. Analysis shows about 20% of hard queries are misrouted to the small model, which then gives confident wrong answers, and regenerate clicks on those threads have doubled. What should you do?
- Your workspace AI retrieves the top-k chunks from a shared vector index and passes them to the model with ACL metadata and a system prompt saying 'only use documents this user can access.' A user just received an answer quoting a private HR page they cannot open. What is the correct fix?
- Your support bot answers billing questions. One user has asked the same refund question three times, and retrieval confidence for that topic is low. What should the bot do next?
- Your AI review system receives a 4,000-line pull request spanning 60 files. Sending the whole diff in one prompt yields shallow, generic comments, and real bugs in files near the middle of the diff are missed. How should you structure the review?
- In your ChatGPT-style assistant, power users keep single threads running for weeks, reaching about 150K tokens. Cost per turn keeps climbing, latency is rising, and the model increasingly misses facts from early in the thread. What should you do?
- Your workspace AI filters retrieval using ACLs stored in the vector index, which is rebuilt nightly. An admin removes an employee from a confidential project page, but for the rest of the day the employee can still get AI answers drawn from it. What is the right fix?