Medium-level LLM and Agentic AI interview questions covering agent architectures, RAG optimization, and production systems. Q1: Design and implement a ReAct (Reasoning + Acting) agent. Answer: How ReAct Works: ReAct alternates between reasoning (thinking) and acting (using tools) to solve problems. Pattern: 1Thought: I …

Retrieval-Augmented Generation techniques for enhancing LLM responses with external knowledge. Core Idea RAG combines retrieval from external knowledge bases with LLM generation to produce accurate, up-to-date responses without retraining the model. Mathematical Foundation The core retrieval mechanism uses cosine …