Ai Coding And Product Systems easy
You are building an AI code assistant with two surfaces: inline ghost-text completion that appears as the user types, and a side-panel chat for questions about the code. Which model strategy best fits both surfaces?
- A Use the single largest model for both surfaces so suggestions and answers share one quality bar.
- B Use a small fast model for chat and a large model for completion, since completions must be exact.
- C Use a small fast model for inline completion and a larger model for the chat panel.
- D Use one mid-sized model for both surfaces and rely on GPU autoscaling to absorb latency spikes.
Answer: C. Use a small fast model for inline completion and a larger model for the chat panel.
Inline completion must land in roughly **200 to 400 ms end to end**, which forces a small model, while chat tolerates seconds and benefits from a larger model's reasoning. Using one large model everywhere (A) is simpler to operate but cannot meet completion latency, so suggestions arrive after the user has typed past them. A single model would only make sense if the product had just one surface, such as chat alone.
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?