Agentic AI and Process Support
Niveau
Master’s degree
Learning outcomes of the courses/module
The participants:
• can explain concepts of agentic AI (e.g., autonomous agents, tool use, planning, orchestration, LLM agents, multi-agent systems) and analyze how they function
• can design AI agent systems that orchestrate multiple components (LLMs, tools, APIs, data sources, subagents)
• can identify appropriate points in business processes for agentic support and design agentic AI solutions for process automation and augmentation
• can apply and evaluate modern agent frameworks (e.g., LangGraph, AutoGen, CrewAI, Hugging Face Agents, ReAct-based systems, OpenAI Assistants/Actions)
• can explain concepts of agentic AI (e.g., autonomous agents, tool use, planning, orchestration, LLM agents, multi-agent systems) and analyze how they function
• can design AI agent systems that orchestrate multiple components (LLMs, tools, APIs, data sources, subagents)
• can identify appropriate points in business processes for agentic support and design agentic AI solutions for process automation and augmentation
• can apply and evaluate modern agent frameworks (e.g., LangGraph, AutoGen, CrewAI, Hugging Face Agents, ReAct-based systems, OpenAI Assistants/Actions)
Prerequisites for the course
none
Course content
- Foundations of agentic AI: concepts, properties, architectures
- Design of agent systems: modularization, orchestration, role models
- Integration into business and knowledge processes
- Frameworks and tools: e.g., LangGraph, AutoGen, CrewAI, Hugging Face Agents, Assistants APIs
- Multi-agent systems: interactions, delegation, collaboration
- Practical development projects
- Design of agent systems: modularization, orchestration, role models
- Integration into business and knowledge processes
- Frameworks and tools: e.g., LangGraph, AutoGen, CrewAI, Hugging Face Agents, Assistants APIs
- Multi-agent systems: interactions, delegation, collaboration
- Practical development projects
Recommended specialist literature
- Bornet, P., Wirtz, J., Davenport, T., De Cremer, D. (2025): Agentic Artificial Intelligence: Harnessing AI Agents to Reinvent Business, Work and Life
- Schneider, M. (2025): Automatisieren mit n8n & KI: Als Einsteiger Workflows erstellen, AI-Agenten nutzen und Prozesse automatisieren
- Kade. S. (2025): AI Agents in Practice: Build, Orchestrate, and Scale Autonomous Systems with LLMs and Multi-Agent Frameworks (The AI Agent Mastery Series, Band 1)
- Lakshaman, V., Hapke, H. (2025): Generative AI Design Patterns: Solutions to Common Challenges When Building Genai Agents and Applications
- Dibia, V. (2025): Designing Multi-Agent Systems: Principles, Patterns, and Implementation for AI Agents
- Gollnick, B. (2025): Generative KI mit Python: KI im Unternehmenskontext – GenAI, Agenten und mehr! Der Guide für RAG-Anwendungen und Agentensysteme mit Vektordatenbanken und LLMs
- Schneider, M. (2025): Automatisieren mit n8n & KI: Als Einsteiger Workflows erstellen, AI-Agenten nutzen und Prozesse automatisieren
- Kade. S. (2025): AI Agents in Practice: Build, Orchestrate, and Scale Autonomous Systems with LLMs and Multi-Agent Frameworks (The AI Agent Mastery Series, Band 1)
- Lakshaman, V., Hapke, H. (2025): Generative AI Design Patterns: Solutions to Common Challenges When Building Genai Agents and Applications
- Dibia, V. (2025): Designing Multi-Agent Systems: Principles, Patterns, and Implementation for AI Agents
- Gollnick, B. (2025): Generative KI mit Python: KI im Unternehmenskontext – GenAI, Agenten und mehr! Der Guide für RAG-Anwendungen und Agentensysteme mit Vektordatenbanken und LLMs
Assessment methods and criteria
Project
Language
German
Number of ECTS credits awarded
6
Semester hours per week
Planned teaching and learning method
Lecture, group work, presentation, and discussion of assignments
Semester/trimester in which the course/module is offered
3