Ai Coding And Product Systems easy
You are building a workspace AI that answers questions over a company's documents. Some documents are visible only to the HR team. Where should the system enforce document permissions?
- A Include each document's ACL in the prompt and instruct the model not to reveal restricted content.
- B Filter retrieval results by the user's permissions before any text reaches the prompt.
- C Index only documents that every employee can read, so no permission checks are ever needed.
- D Let the model answer freely, then scan the output for restricted keywords before returning it.
Answer: B. Filter retrieval results by the user's permissions before any text reaches the prompt.
The **retrieval layer** must enforce permissions, because anything placed in the prompt can leak through paraphrase or prompt injection. Asking the model to respect ACLs (A) seems convenient, but the model is not a security boundary. Indexing only public documents (C) is safe yet gives up most of the useful content; it is acceptable only when nearly everything is already shared.
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?