Generative Artificial Intelligence for Managers

 Type of module (compulsory / elective)

Compulsory

Level of the module (according to EQF: first cycle Bachelor / second cycle Master)

EQF-Level 7; Master’s level

Academic Year

1

Semester in which the module is offered

Winter semester

Duration of the module

One semester

Total workload

180 hrs

(48 hrs attendance, 132 hrs self-study)

Usability of the module

Independent module

Number of ECTS credits assigned

6

Name of the lecturer(s)

Prof. Dr. Christoph Ihl

Learning outcomes of the module

Upon completion of this module, students will be able to:

·        Understand LLM architecture, capabilities and limitations.

·        Master advanced prompting techniques.

·        Extract structured data from unstructured text.

·        Build knowledge bases and implement RAG pipelines.

·        Design autonomous agents and implement tool use and multi-step reasoning.

·        Analyze business data with the help of GenAI.

·        Interpret and communicate ML results with the help of GenAI.

·        Apply frameworks to identify valuable GenAI business applications.

·        Develop GenAI product proposals.

Type of course (face-to-face, distance learning)

Designed as a digital learning path

Prerequisites according to curriculum

None

Course content

·        Introduction to LLMs

·        Advanced Prompting & Extraction

·        Retrieval-Augmented Generation

·        GenAI Agents

·        GenAI-Assisted Machine Learning

·        GenAI Business Cases

 

Recommended or obligatory literature

·        Alammar, J., & Grootendorst, M. (2024). Hands-on large language models: language understanding and generation. O’Reilly Media.

Examination method

·        5 individual in-class assignments and a final team project

Module Grading Breakdown

·        10% per in-class assignment and 50% for the final team project

Teaching method

·        Theory/Conceptual Input: Foundation building through lectures, demonstrations, and discussions.

·        Guided Lab Session: Instructor-led walkthrough of implementation notebooks.

·        Independent/Peer Lab Session: Self-paced or collaborative work on practice notebooks.

·        In-Class Assignment: Application of learned concepts to solve

business problems.

Language of instruction

English