Ai Coding And Product Systems easy
Your AI assistant is launching a free tier alongside a paid plan. Inference is your largest cost, and free users are expected to outnumber paid users by a wide margin. How should the free tier be designed?
- A Route free users to a smaller model with hard daily token budgets and shorter context limits.
- B Give free users the same model and limits as paid users to maximize conversion to paid plans.
- C Give free users the same model and limits but queue their requests behind paid traffic at peak.
- D Rely on per-IP request rate limits alone, since token usage per request is roughly constant.
Answer: A. Route free users to a smaller model with hard daily token budgets and shorter context limits.
Free tiers need **hard token budgets and degraded models** to keep cost bounded, trading some quality for a sustainable unit cost. Same model and limits (B) maximizes the free experience, but a large free user base would then burn the bulk of inference spend. Request limits alone (D) fail because one request can use a few hundred tokens or tens of thousands.
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?