Ai Coding And Product Systems hard
Your answer engine shows about 12 citations per answer. An audit finds that roughly half of the cited pages do not actually support the sentence they are attached to, and user trust surveys are falling. What should the team optimize?
- A Raise the citation count to 15 or more so each claim has several sources and any single unsupported link is diluted by the others.
- B Retrieve 100 or more web results per query so the generator has a larger candidate pool from which to pick supporting passages.
- C Verify each claim against its passage with an entailment check and cite only supporting passages, typically 3 to 8 of them.
- D Restrict citations to high-authority domains, since reputable sites are much less likely to be cited for claims they never make.
Answer: C. Verify each claim against its passage with an entailment check and cite only supporting passages, typically 3 to 8 of them.
Trust comes from **citation precision**, not citation count. A verification pass costs latency and shows fewer links, but every link it shows holds up when clicked. Adding citations (A) is the common misconception: users who click unsupported links lose trust no matter how many others exist. Domain authority (D) ranks sources but cannot tell whether a given passage entails a given claim.
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?