← MSBAi Home

Generative AI for Analytics (BADM 5XX or MSBAi550A)

Program-level details: See program/CURRICULUM.md

Status: TBD (pending approval)

Credits: 2 Term: Spring 2027 (Weeks 5-8, concurrent with BADM 558 second half)

Course Vision

Students move beyond prompt engineering to build AI-powered analytics systems. The course covers LLM fundamentals, Retrieval-Augmented Generation (RAG) pipelines, and agentic AI patterns — equipping graduates to build internal AI tools, not just use them. By course end, students can design and implement RAG systems and agent-based workflows for real analytics problems.


Learning Outcomes (L-C-E Framework)

Literacy:

Competency:

Expertise:


Week-by-Week Breakdown

Week Topic Activities Assessment
1 LLM fundamentals + prompt engineering Transformer architecture overview, prompt patterns for analytics (chain-of-thought, few-shot), AI for SQL/Python generation Prompt engineering exercises
2 RAG implementation LangChain fundamentals, document chunking strategies, embedding models (OpenAI Embeddings API), vector databases (ChromaDB/Pinecone), retrieval evaluation Project 1: RAG pipeline
3 Agentic AI patterns + governance Function calling, tool use, multi-agent intro, orchestration patterns, NIST AI RMF overview, AI governance basics Agentic AI lab
4 Capstone project + ethics Build RAG or agent-based analytics workflow, ethics case study, responsible AI checklist Project 2: Agentic capstone + oral defense

Projects (2 major, both individual — 4-week course)

Project 1: RAG Pipeline (Weeks 1-2, Individual, 40% of grade)

Project 2: Agentic Capstone (Weeks 3-4, Individual, 50% of grade)

Studio Participation: 10% of grade


Assessment Summary

Component Weight Notes
Project 1 (RAG Pipeline) 40% Weeks 1-2, individual
Project 2 (Agentic Capstone) 50% Weeks 3-4, individual, includes oral defense
Studio participation 10% Weekly attendance

No traditional exam. Project-based with AI systems focus.


Rubric (5 dimensions)

Dimension Excellent (A) Proficient (B) Developing (C)
RAG Implementation Well-architected pipeline, strong retrieval accuracy, justified chunking/embedding choices Functional pipeline, adequate accuracy Basic implementation, poor retrieval quality
Agentic Design Sophisticated agent patterns, effective tool use, handles edge cases Functional agent, basic tool integration Minimal agent functionality
AI Governance Comprehensive model card, risk assessment, NIST alignment Adequate governance documentation Minimal or missing governance
Code Quality Production-ready, well-documented, tested Functional with minor issues AI code has problems
Oral Defense Explains architecture clearly, handles questions confidently, articulates trade-offs Adequate explanation, answers most questions Cannot explain choices or struggles with Q&A

Technology Stack

Prerequisites


Last Updated: February 2026