Ai Coding And Product Systems easy
Your AI code review system receives a 3,000-line pull request that touches 40 files. How should it feed the changes to the model?
- A Send the entire diff in one prompt so the model can see every cross-file relationship at once.
- B Review only the first file in the diff, since large pull requests are usually mechanical changes.
- C Split the diff into fixed 500-line windows regardless of file or function boundaries for evenness.
- D Chunk by file or hunk with nearby code context, adding related definitions as needed.
Answer: D. Chunk by file or hunk with nearby code context, adding related definitions as needed.
**Chunking along file and hunk boundaries** with nearby context gives up some whole-PR visibility in exchange for focused prompts that yield precise comments. A single giant prompt (A) is tempting for cross-file awareness, but attention gets diluted and comment quality drops on large diffs. Sending the whole diff works well only for small pull requests.
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?