AWS Databricks Platform Architect

In this course, you will learn how to design, implement, and govern catalog structures and large-scale data organization on the Databricks Data Intelligence Platform. It offers a comprehensive view of Unity Catalog as the centralized governance layer for an enterprise lakehouse. Divided into five modules, it begins by placing Unity Catalog within the cloud deployment model — covering the Account Console, metastore creation, and the administrator role hierarchy. You will then translate organizational topology (business units, regions, and dev/QA/prod environments) into a scalable catalog and schema design using naming conventions, ownership patterns, and MANAGE delegation. The course then covers secure storage integration with storage credentials, external locations, the managed-storage hierarchy, managed versus external tables, and UC Volumes for non-tabular data. Next, you will apply access patterns and isolation strategies — the three-level GRANT chain, workspace-catalog binding, and schema-level Attribute-Based Access Control (ABAC) policies — to enforce fine-grained data protection at scale. Finally, the course closes with best practices for catalog design, automation, least-privilege permissions, and group-based access management.

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.

本课程教授学生如何使用 MLflow 的评估框架对 AI 智能体进行系统性评估，以应对传统软件测试无法处理的非确定性 AI 系统所带来的独特挑战。学生将评估一个已注册在 Unity Catalog 中并通过 Unity Gateway 调用其模型的共享工具调用智能体，使用内置评判器处理正确性和安全性等常见标准，使用准则评判器满足特定业务需求，并使用自定义评判器应对专项需求。本课程涵盖使用精选数据集进行离线评估和在线生产监控，包括在 Unity Catalog 中存储 MLflow Traces。学生将使用 MLflow Tracing 了解智能体的执行模式，并收集来自开发人员和主题专家的人工反馈，这些专家通过 Databricks App 对智能体进行审查。通过实践演示和实验，学生将掌握创建评估 Workflows 的技能，从而在 AI 智能体开发生命周期中持续推动质量提升。

注意：对于 SCORM 讲授文件，请确保在完成内容后关闭 SCORM 窗口。请勿点击“Next Lesson”按钮，否则可能导致 SCORM 模块无法被标记为已完成。

提示公司 AI Assistant 的两部分基础课程。第一部分（基础知识）阐释提示的具体程度如何影响回答质量，将该助手定位为一位才华横溢但严格按字面理解指令、通过 RAG 架构扎根于内部知识的"实习生"，介绍其可访问与不可访问的内容，强调"信任但需核实"的思维方式，并引入 C-O-I-E 框架（Context、Outcome、Instruction、Example）。第二部分（技巧）构建提示技巧工具箱，并讲授如何在各技巧之间做出选择：将任务与方法相匹配、内容生成（零样本与少样本）、推理（思维链、自问自答、元提示）、工作流（提示链接以及何时使用链接而非单一提示），以及如何清晰地组织提示结构。