Engineering Knowledge & Data Infrastructure

Seminar Overview

Every engineering organization sits on decades of specifications, test reports, failure records, and standards — mostly unfindable. This course teaches the practical discipline of engineering knowledge infrastructure: getting documents into a searchable, citable corpus, how modern retrieval (keyword, vector, and hybrid search) actually works, how retrieval-augmented generation grounds AI answers in your corpus, and how to measure corpus quality instead of guessing.

The course uses the ETS knowledge corpus — 41 years of failure records, primary standards, and handbooks — as the worked example, then helps attendees map their own: what to ingest, how to structure it, metadata and access control, retention and regulatory constraints, and the maintenance loop that keeps a knowledge base alive after the project ends. This is the connective tissue course: it powers ChatETS corpus work, any RAG initiative, and plain search-and-find improvements.

Ideal Learner

• Engineering managers owning institutional knowledge and lessons learned
• Knowledge-management and IT staff building document systems
• Quality and compliance teams whose records must stay findable
• Teams preparing their corpus for ChatETS or other RAG deployment

Learning Objectives

• Inventory and classify an engineering document estate for retrieval
• Build document pipelines: ingestion, OCR, structure, metadata
• Explain and choose between keyword, vector, and hybrid retrieval
• Ground AI answers in your corpus with correct citations
• Operate the corpus: governance, access control, retention, refresh

Consulting Sessions

Seminar attendees can sign up for individual consulting sessions with the instructor. Sessions are free for registered attendees, first-come first-served — sign up when registering by calling 248-539-0473 or during the seminar.