Get Started with Lakehouse Architecture on Databricks - Mandarin Chinese

This course provides a comprehensive, hands-on overview of Databricks' modern approach to data warehousing, highlighting how a data lakehouse architecture combines the strengths of traditional data warehouses with the flexibility and scalability of the cloud. Working end-to-end with a fictional retailer (Vintage Audio Co.), you will explore the workspace, query governed Unity Catalog tables, keep Delta tables fast for analytical reads, load data incrementally with Auto Loader, model a star schema, and deliver consistent insights through Unity Catalog metric views — all from a single, governed environment, with AI-driven features (Predictive Optimization, Genie Code) built in throughout.

AI has changed what developers are asked to build: agents, copilots and intelligent tools are moving from experiments into production, and the work is shifting from writing code to orchestrating models, data, and services. In this course, you'll learn how building agentic applications where the data lives removes the infrastructure overhead of stitching together fragmented stacks. Through a guided account-briefing demo, you'll see how Databricks Apps, Lakebase, and Agent Bricks (Genie Spaces, Knowledge Assistants and Supervisor Agents) work together on one governed, serverless foundation to deliver a production-ready agentic application.

This course teaches students how to systematically evaluate AI agents using MLflow's evaluation framework, addressing the unique challenges of non-deterministic AI systems that traditional software testing cannot handle. Students learn to implement various evaluation approaches including built-in judges for common criteria like correctness and safety, guideline judges for business-specific requirements, and custom judges for specialized needs. The course covers both offline evaluation using curated datasets and online production monitoring, with hands-on experience using MLflow's tracing capabilities to understand agent execution patterns and collect human feedback from different stakeholder types. Through practical demonstrations and labs, students develop skills in creating evaluation workflows that drive continuous quality improvements throughout the AI agent development lifecycle.

Note: For SCORM lecture files, please ensure that you close the SCORM window after completing the content. Do not click the ‘Next Lesson’ button, as doing so may prevent the SCORM module from being marked as complete.