Ai Coding And Product Systems easy
Enterprise customers are evaluating your AI code assistant and are worried about how their proprietary source code will be handled. Which design best addresses their concern?
- A Use one shared embedding index across all customers so common code patterns improve results.
- B Train the base model on customer code by default, letting customers opt out in their settings.
- C Keep per-tenant indexes and do not train on customer code unless a customer explicitly opts in.
- D Encrypt code in transit only, since the index is internal and not reachable from the internet.
Answer: C. Keep per-tenant indexes and do not train on customer code unless a customer explicitly opts in.
**Tenant-scoped indexes** and **no training on customer data by default** give up cross-customer learning in exchange for strong isolation. A default-on training policy with opt-out (B) improves the model but can let one customer's code surface in another's suggestions. Shared learning is acceptable only for public open-source code or for customers who explicitly opt in.
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?