Ai Coding And Product Systems easy
A user of your code assistant's chat asks "How does authentication work in this project?" inside a monorepo with millions of lines of code. How should the system assemble context for the model?
- A Send the entire repository in the prompt so the model can see every possibly relevant file.
- B Send only the currently open file, since the user's question almost always concerns that file.
- C Fine-tune a model on the repository nightly so it memorizes the code and needs no context.
- D Retrieve and rank candidate files from an index, then pack the top results into a budget.
Answer: D. Retrieve and rank candidate files from an index, then pack the top results into a budget.
**Retrieval and ranking** of files trades indexing work for prompts that are small, cheap, and focused on the code that matters. Sending the whole repo (A) is tempting because nothing is missed, but it exceeds the context window, costs a lot, and buries the relevant files in noise. Sending everything only works for a tiny repo that fits comfortably in context.
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?