# Easy Data x AI

An introductory Chinese-language course on data and AI fundamentals, teaching how to build AI agents from a data-driven perspective through two parallel learning tracks.

Easy Data x AI is an alpha-stage, community-built course introducing data and AI fundamentals to a broad audience, from AI enthusiasts with no technical background to developers already calling large language model APIs. It is split into two parallel tracks: a conceptual track for product decision-makers and beginners covering when a task suits an agent, a framework for diagnosing whether a problem lies in data, the model, or the business layer, and the product design behind retrieval-augmented generation, MCP, skills, and memory; and a hands-on developer track covering streaming output and tool use, building a data layer on a lightweight AI-native database, comparing hybrid retrieval against pure vector retrieval, and building an agent with a memory system and skills.

A further industry-practice section extends the developer track with topics such as AI-native databases, vector databases and retrieval-augmented generation, SQL-based AI functions, and context engineering, aimed at developers wanting production-level detail.

It is written in Python and Chinese, and is hosted with an online reading site and community classroom sessions.

Website: https://datawhalechina.github.io/easy-data-x-ai/