Ai Coding And Product Systems easy
Your chat assistant takes about 8 seconds to generate a full answer, and users report that the app feels frozen or broken while they wait. Which change best improves the experience?
- A Wait for the full response, then return it at once so users never see a partially written answer.
- B Stream tokens to the client over SSE as they generate, so first text appears in under a second.
- C Cache every answer by exact prompt text so repeated questions return instantly from storage.
- D Switch to a much smaller model for all chat so the full answer finishes in under one second.
Answer: B. Stream tokens to the client over SSE as they generate, so first text appears in under a second.
**Streaming** cuts perceived latency to the **time to first token** without lowering answer quality, even though total generation time is unchanged. A much smaller model (D) does shorten total time, but it gives up the reasoning quality that chat is supposed to provide. Returning the whole answer at once (A) suits API clients that need complete structured output, not interactive chat.
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?