Design a chatbot fallback for unknown questions

Q: Design a chatbot fallback for unknown questions

This is a ML System Design interview question from OpenAI for Machine Learning Engineer roles. View the full question and solution on PracHub.

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

Scenario

You run a ChatGPT-like assistant. Users sometimes ask questions the model cannot answer reliably (unknown/uncertain/needs up-to-date facts).

Task

Design a system that improves user experience and answer quality when the assistant "doesn't know".

Requirements

The assistant should avoid hallucinations and be transparent about uncertainty.
It should still help the user make progress (clarify, retrieve sources, route to tools, etc.).
Support both factual queries (need citations) and personal/workflow queries (need clarification).
Low latency for common queries; allow slower tool usage when needed.

Deliverables

High-level architecture (LLM, retrieval, tools, policies).
Decision policy for: answer directly vs. ask clarifying questions vs. retrieve vs. refuse.
How you evaluate success (offline and online metrics) and handle failure modes.

Design a chatbot fallback for unknown questions

Scenario

Task

Requirements

Deliverables

Solution

Comments (0)