Agentic AI Interview Kit
An open-source study guide of more than 60 pages covering agentic AI from LLM foundations through production system design, framework walkthroughs and an interview question bank.
This guide is organized into seven progressive sections: foundations covering LLM internals, prompting, embeddings, RAG, fine-tuning and evaluation metrics; core concepts such as the agent loop, tool use, memory architectures and guardrails; design patterns including ReAct, chain-of-thought, reflection, multi-agent and plan-and-execute; framework walkthroughs for LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, LlamaIndex and OpenAI's tooling; and runnable implementations of a ReAct agent, a RAG agent, a multi-agent crew, a LangGraph workflow and an evaluation harness.
A system-design section covers orchestration, state management, tool registries, observability and security principles, alongside case studies for a customer-support agent, a code assistant, a data pipeline, a research agent and nine more scenarios.
The interview-prep section provides a question bank spanning foundational, architecture, design-pattern, system-design, framework, coding and behavioral questions. It is built with Docusaurus and requires Node.js 20 or newer to run locally.