AI Agents & PrivacyModule description #41267 / Version 1
- 6 CP
- Oral exam
- Graded
- Winter semester
- English
| Module / Version | #41267 / #1 |
|---|---|
| Validity | Since Winter semester 2025/26 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Küpper, Axel |
| Grading | Graded |
| Exam format | Oral exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Telekommunikationssysteme |
| Academic chair | 34335700 FG S-Professur Service Centric Networking (SNET) |
Contact
| Office | BH-N SNET |
|---|---|
| Contact person | Küpper, Axel |
| E-mail address | axel.kuepper@tu-berlin.de |
| Website | https://www.tu.berlin/snet/ |
Learning outcomes
Students have basic knowledge of the legal requirements for processing digital identity information and thus personal data of individuals. They are familiar with methods and practices for collecting personal data and the associated risks they pose to individual privacy. They are familiar with mechanisms for implementing the privacy-by-design principle and various solutions for anonymising personal data.
Content
The lecture "AI Agents" starts with an introduction to the concepts, architectures, and application domains of agentic systems, with a particular focus on recent developments in the field of Large Language Models (LLMs). It begins by introducing fundamental terms and definitions, types of agents such as reactive, deliberative, and hybrid agents, classical and modern agent architectures, as well as communication and interaction interfaces. The goal is to establish a solid understanding of the structural and functional foundations of AI agents. Building on this, the lecture focuses on the technical foundations of LLM-based agent systems. Central topics include prompt engineering, function calling, retrieval-augmented generation, multimodality, and chain-of-thought reasoning for step-by-step problem solving. The role of reinforcement learning in decision-making - especially in combination with LLMs - is also addressed, along with topics such as reward modeling, action planning, and adaptation to dynamic environments. Another key focus is the integration and orchestration of AI agents through interfaces and protocols such as the Model Context Protocol (MCP) or the OpenAI API. A dedicated module covers cooperation and coordination mechanisms in multi-agent systems, enabling multiple AI agents to collaboratively plan, exchange knowledge, and solve complex tasks together. The lecture is practice-oriented and accompanied by concrete examples and hands-on exercises. Contemporary development and execution platforms such as LangChain, AutoGen, CrewAI, and Semantic Kernel are used. Using these tools, students learn how to model, implement, and test AI agent systems. Existing implementations such as AutoGPT or BabyAGI are also analyzed, compared, and evaluated in terms of their architecture, performance, and practical relevance. In addition, the lecture also addresses interdisciplinary topics that are essential for the development and practical deployment of AI agents. These include questions of explainability and transparency in decision-making, as well as security-related aspects such as identity management for AI agents. This is complemented by a critical examination of ethical and societal issues, especially in the context of autonomous decisions, accountability, and trust in AI agent systems. Finally, aspects such as scalability and resource usage - regarding computing power, API costs, or energy efficiency - as well as considerations of software architecture and deployment are discussed.
In the area of digital privacy, legal framework conditions for the processing of personal data are taught. In particular, the legal provisions of the General Data Protection Regulation (GDPR) are taken into consideration. In order to present mechanisms and solutions for data collection, a focus is placed on various tracking methods in the context of web and mobile applications. This is followed by a presentation of various approaches (privacy-by-design, privacy-by-default, etc.) for implementing principles and techniques to improve digital privacy. In addition, various methods for anonymising personal data are presented and metrics (k-anonymity, L-diversity, T-closeness, etc.) for quantifying these are taught.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| AI Agents | Lecture | Winter semester | [en] | 2 | WS 2026/27 (1) ISIS | |
| Privacy Fundamentals | Lecture | Winter semester | [en] | 2 | WS 2026/27 (1) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Privacy Fundamentals (Lecture) 1
- Privacy Fundamentals (Vorlesung) Termingruppe 1
Workload and credit points
AI Agents (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Privacy Fundamentals (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
This module has no desirable prerequisites for the courses.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Oral exam |
| Language | English, German |
| Duration/Extent | 30 minutes |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
The maximum capacity of participants is 20.
Registration procedures
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available – Supplementary materials such as research papers, assignments, links, and presentation slides will be made available through the online forum.
Recommended literature
No recommended literature given
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks |
| SS 2026 | Wahlpflicht Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | WS 2025/26 | Studiengebiete › Verteilte Systeme und Netze / Distributed Systems and Networks |
| SS 2026 | Studiengebiete › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks |
| SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2026 | WS 2026/27 | Engineering Sciences / Specialization › Software Systems Engineering › Distributed Systems and Networks |
| Information Systems Management (Wirtschaftsinformatik) Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017 | WS 2025/26 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks |
| SS 2026 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| WS 2026/27 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks |
Miscellaneous
Not specified