Module 3 Narration#
Opening#
Open with the professional setting: a platform team designing data infrastructure for repeatable model training and monitoring. Ask students what decision is being made, who is affected, and what evidence would be persuasive to a skeptical reviewer.
Middle#
Move through the module in four passes:
Define Storage, indexing, and retrieval in the context of Big Data Management for AI Applications.
Walk through the lab as a proxy-data exercise, emphasizing what it can and cannot show.
Compare a baseline with an AI-enabled or more sophisticated alternative.
Translate the result into stakeholder language: recommendation, risk, mitigation, and next evidence.
Closing#
Close by returning to the module artifact: AI data platform design review with lineage, quality checks, cost controls, and access model focused on storage, indexing, and retrieval: Compare tabular, document, and vector storage options.. Students should leave knowing exactly what artifact they are producing and how it will be judged.