Generative AI (DigiBIM)

This is the webseite for the lecture “Generative AI: Large Language Models” (MSB.2.0184.0.V.1) in the Masters programm “Digital Business and Innovation Management” by Prof. Dr. Michael Bücker.

“AI won’t replace you, but someone using AI will.”
— often attributed to Kai-Fu Lee / Andrew Ng

Course Overview

This course introduces students to the foundations, applications, and frontiers of Generative AI, with a special focus on Large Language Models (LLMs) and AI Agents.
Together we will explore how these systems work, how they can be applied in business and research, and what challenges and opportunities they create for society.

  • Foundations: Python basics, APIs, and Natural Language Processing
  • LLM Fundamentals: tokenization, embeddings, attention, alignment
  • Applications: prompting, function calling, memory, retrieval (RAG)
  • Advanced Topics: orchestration, interoperability, governance, and the EU AI Act

The course combines theory, live coding, and hands-on projects. Students will learn not only to use existing AI tools, but also to design and implement their own intelligent workflows.

Why This Matters

AI is rapidly moving from research labs into everyday work:

  • Automating tasks (e.g., Copilot, ChatGPT)
  • Supporting decision-making with data analysis and predictions
  • Enabling new business models and opportunities

This course will help you understand, apply, and critically reflect on these developments.

The AI Agent Framework

In recent years, large language models have shown impressive capabilities, but their true potential unfolds when they are embedded into so-called AI agents: systems that combine reasoning with tools, memory, orchestration, and governance. This framework allows them not only to generate text, but also to interact with data, automate workflows, and act responsibly within defined boundaries. Exploring and applying this concept of AI agents forms the core of our lecture.

Figure 1: AI agents extend LLMs with tools, memory, orchestration, and governance — enabling them to act autonomously and safely on behalf of users.

Examination & Assessment

The main deliverable is a group project (3–5 students). For details see the assignment description.

Practical Information

  • Format: weekly lectures with integrated coding sessions
  • Tools: Python, Jupyter, VS Code
  • Resources: slides, code, and readings in the course repository
  • Communication: via MS Teams
Back to top