Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

AI InfrastructuresModule description #41265 / Version 1

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27). Current version (v2)
Module / Version#41265 / #1
ValidityWinter semester 2025/26 – Summer semester 2026
Available language(s)English, German
Credit points6
Person responsible for the moduleKüpper, Axel
GradingGraded
Exam formatOral exam
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Telekommunikationssysteme
Academic chair34335700 FG S-Professur Service Centric Networking (SNET)

Contact

OfficeBH-N SNET
Contact personKüpper, Axel
E-mail addressaxel.kuepper@tu-berlin.de
Websitehttps://www.tu.berlin/snet/

Learning outcomes

The students understand how AI agents, with the help of Large Language Models (LLMs), are capable to perform complex tasks largely autonomously. They know how AI agents are designed and implemented, and what role these agents can play in future software systems, particularly in the context of automation and decision support. They are familiar with common agent types, multi-agent architectures, as well as communication, cooperation, and coordination patterns and AI interfaces relevant to designing automation processes with multi-agent systems. Students understand fundamental principles of perception, decision-making/planning, memory management, and action execution in AI agents. They are capable of independently developing a multi-agent system using appropriate agent frameworks and of systematically analyzing and evaluating its behavior regarding goal achievement, efficiency, and robustness.

Students understand what Internet-based services and APIs are, how they are conceptualized, implemented, and documented, and the role they play in developing modern software and system architectures. They are familiar with common design patterns, protocols, and standards relevant to the design of services and APIs. Students know fundamental principles of API management as well as relevant legal and organizational frameworks, and they understand the significance of API ecosystems. They can evaluate existing API designs regarding quality, security, and usability, and independently develop solutions to typical challenges.

Content

The module teaches the basics of AI agents and Internet-based services and APIs.

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.

The field of Service & API Design begins by introducing basic terminology and fundamental concepts such as interfaces, APIs, and web-based services. This is followed by an overview of microservices as a key architectural style for developing modern, distributed systems. Typical characteristics, advantages, and challenges of microservice architectures are discussed in detail, including service granularity, independent deployment, scalability, and service communication and coordination. Complementing this, container technologies like Docker and orchestration systems such as Kubernetes are introduced, emphasizing their relevance for operating and managing microservices. Subsequently, essential API design principles and approaches, particularly REST, gRPC, and GraphQL, are covered, highlighting their typical use cases, strengths, and weaknesses. Important aspects of API design, including versioning, error handling, documentation, and testability, are also addressed. Finally, the module provides an overview of relevant standards and formats such as OpenAPI, JSON, and XML, as well as communication protocols like HTTP and CoAP. Advanced topics like API governance and current technological developments complete the module.

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
AI AgentsLecture Winter semester[en]2 ISIS
Service & API DesignLecture Winter semester[en]2 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (2)

AI Agents (Lecture) 1

All groups of this course in the catalog

Service & API Design (Lecture) 1

All groups of this course in the catalog

Workload and credit points

AI Agents (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Service & API Design (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 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

The content is taught in two lectures in which a thematic dialogue between students and the lecturer is sought. The content of the lectures is deepened through practical examples on the web and in the form of scientific publications.

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

GradingGraded
Exam formatOral exam
LanguageEnglish, German
Duration/Extent30 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

Students can enroll in this course during the first week of the semester. Detailed information on the enrollment process will be provided via ISIS.

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 versionSemester(s)Curriculum component
Computer Engineering
Computer Engineering (M. Sc.) - StuPO 2015
WS 2025/26Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks
SS 2026Wahlpflicht Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks
Computer Science (Informatik)
Computer Science (Informatik) (M. Sc.) - StuPO 2015
WS 2025/26Studiengebiete › Verteilte Systeme und Netze / Distributed Systems and Networks
SS 2026Studiengebiete › Verteilte Systeme und Netze / Distributed Systems and Networks
Electrical Engineering
Electrical Engineering (M. Sc.) - StuPO 2015
WS 2025/26Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks
SS 2026Wahlpflicht Studiengebiet Kommunikationssysteme / Communication Systems › Wahlpflicht Studienrichtung Kommunikationssysteme / Communication Systems
Industrial Engineering and Management
Industrial Engineering and Management (M. Sc.) - StuPO 2015
WS 2025/26Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Data and Software Engineering
SS 2026Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Data and Software Engineering
Information Systems Management (Wirtschaftsinformatik)
Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017
WS 2025/26Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks
SS 2026Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks

Miscellaneous

Not specified