Design AI chat bot system

Q: Design AI chat bot system

This question evaluates understanding of ML system design and front-end–centric architectures, focusing on browser-only state management, streaming LLM responses, SPA lifecycle constraints, stateless relay integration, and credential/security considerations.

Q: How do I approach ML System Design interview questions?

ML System Design questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master ml system design interviews.

Question

System Design: In-Browser AI Chat With Streaming

Requirements

Design a web-based AI chatbot system that satisfies all of the following:

User messages and full conversation history are stored only in the browser (no backend database or server-side persistence).
Bot responses are streamed to the user token-by-token (or chunk-by-chunk).
Refreshing the page starts a new conversation (no history survives a reload).
Handle user credential and security considerations.

Assume a typical SPA front end and that you may use a stateless backend relay to call an external LLM provider, but you must not persist user messages server-side.

Design AI chat bot system

System Design: In-Browser AI Chat With Streaming

Requirements

Solution

Comments (0)