Concepts and techniques of GenAI for business-oriented applications, including prompt engineering, agents, retrieval augmented generation, foundation model fine-tuning and pretraining, and multimodal models. Responsible GenAI topics, such as copyright infringement, toxicity, bias, and hallucination are also covered. The emphasis is on the design and implementation of basic business-oriented GenAI applications.
Athena Title
Generative AI
Prerequisite
MIST 4600 or MIST 4600E or MIST 4605
Grading System
A - F (Traditional)
Student learning Outcomes
Students will apply foundational Generative AI (GenAI) techniques, such as prompt engineering ,Retrieval Augmented Generation (RAG), and agentic AI, to orchestrate solutions for identified business needs and organizational decision-making.
Through the application development project, students will design and implement a novel, business-oriented GenAI application by selecting and configuring foundation models, and will evaluate its task performance using systematic, quantifiable metrics.
Students will critically analyze the ethical, social, and operational challenges of deploying GenAI solutions in organizations, including evaluating risks related to toxicity, bias, hallucination, copyright infringement, and data security.
Topical Outline
GenAI business use cases
GenAI architecture, ecosystem, and orchestration
Reasoning and prompt engineering
Prompting-based AI agents
Retrieval augmented generation (RAG)
Foundation models and pretraining
LLM fine-tuning and alignment
Multimodal LLM
Responsible GenAI
Institutional Competencies Learning Outcomes
Analytical Thinking
The ability to reason, interpret, analyze, and solve problems from a wide array of authentic contexts.
Critical Thinking
The ability to pursue and comprehensively evaluate information before accepting or establishing a conclusion, decision, or action.
