Ai Coding And Product Systems easy
Your inline code completion fires a request on every keystroke. The GPU fleet is overloaded, and p95 latency is well above 400 ms. Which change helps most?
- A Move completion onto the large chat model, which has spare capacity during business hours.
- B Debounce requests, cancel stale ones, and cache results keyed on the typed prefix.
- C Expand the completion context to the whole repository so fewer follow-up requests occur.
- D Queue every keystroke request in order so the user eventually sees each suggestion in turn.
Answer: B. Debounce requests, cancel stale ones, and cache results keyed on the typed prefix.
**Debouncing, cancellation, and prefix caching** remove wasted work, which is what makes the latency target reachable. In exchange, a suggestion may appear a beat later after a pause in typing. Queuing every request (D) preserves all suggestions, but most are stale by the time they arrive and the queue adds latency. Processing every request matters only when each one is independently useful, which keystroke completions are not.
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?