33Users want to ask questions about hour-long recorded lectures and meetings. What does one question cost, and what do you build?▼hardNewGoogleGoogle DeepMind◆ premiumSending the whole video with every question costs about a quarter of a million tokens. Index it once, retrieve the right minutes and keep the whole-video pass for one-off questions.Practise this question →Read answer →
18Engineering wants a semantic cache that reuses answers to similar questions. What could go wrong, and how would you design it safely?▼hardNewPerplexityGleanIntercom◆ premiumA cost lever that can silently serve wrong answers and leak one user's data to another. The interviewer wants the failure modes and a design that keeps the savings where they are safe.Practise this question →Read answer →
11Design the pricing structure for a model API with several model tiers. What levers do you use, and how do you avoid surprising customers?▼hardNewAnthropicOpenAIGoogle◆ premiumAPI pricing shapes which products developers can build. The interviewer wants tier spread, input and output pricing, discounts that reward efficient usage, enterprise commitments, and predictability.Practise this question →Read answer →
39Our API is stateless. Should we store conversation state on the server, and what happens to customers who can't let us store anything?▼hardNewOpenAI◆ premiumServer-side state simplifies integration and can improve caching, but it means storing data and it does not make old tokens free. Offer it as an option with short retention and give zero-retention customers an equal stateless path.Practise this question →Read answer →