Ai Coding And Product Systems hard
Free users consume 70% of your assistant's GPU hours but bring in about 5% of revenue through conversions. Leadership wants to keep the free tier useful enough to drive upgrades. Which policy fits?
- A Enforce per-user daily token budgets, route free traffic to a smaller model, and degrade to queued service once budgets run out.
- B Serve free users the same model to showcase full quality, with per-minute request rate limits identical to the paid tier's limits.
- C Serve free users the same model but cap output tokens per response, since output tokens dominate the cost of each request.
- D Rely on per-IP request rate limits at the API gateway, because per-token accounting adds measurable latency to every request.
Answer: A. Enforce per-user daily token budgets, route free traffic to a smaller model, and degrade to queued service once budgets run out.
Free tiers need **hard token budgets and degraded models**. You give up showing peak quality but put a ceiling on cost per free user. Request rate limits (B, D) do not bound spend, because one request with a long context can cost 100x a short one. Capping output (C) ignores input and prefill cost, which dominates for long threads and file uploads.
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?