Ai Coding And Product Systems easy
Your answer engine retrieves about 20 web results per query. A product manager proposes citing all 20 sources under every answer to increase user trust. What is the main problem with this idea?
- A Nothing; more citations always improve trust, so cite every result the system retrieved.
- B Citations are cosmetic; users trust fluent answers, so citation count has little effect at all.
- C Trust depends on each citation supporting its claim; padding adds weak links.
- D Citations should be removed, because the model's own knowledge is more reliable than web search.
Answer: C. Trust depends on each citation supporting its claim; padding adds weak links.
Answer engines typically retrieve **10 to 30 results but cite 3 to 8**, because **citation precision**, not count, earns trust. Citing everything (A) looks thorough, but users who click a citation that does not support the claim stop trusting the whole answer. Long source lists make sense only as a separate "further reading" list, kept apart from inline claims.
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?