Ai Coding And Product Systems easy
You are designing an answer engine that searches the web and returns a cited answer within a latency budget of a few seconds. Where should most of the budget and engineering effort go?
- A Generating long, detailed answers with the largest model, since answer length signals quality.
- B Rendering the answer UI, since users judge the product mainly by how its citations are laid out.
- C Skipping search and answering from model memory, then attaching matching links afterward.
- D Retrieving and ranking 10 to 30 sources well, so the generator cites a few highly relevant ones.
Answer: D. Retrieving and ranking 10 to 30 sources well, so the generator cites a few highly relevant ones.
An answer engine's quality is capped by **retrieval and ranking**, so the budget goes there rather than into a bigger generator. Answering from memory and attaching links afterward (C) is faster, but the citations often do not support the claims, and the answers miss recent events. Leaning on the model's memory is reasonable only for stable, general-knowledge questions.
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?