TU-EV00037 - AI Agents and the Real World, Lectures, 29.4.2025-3.6.2025

Please note! Course description is confirmed for two academic years, which means that in general, e.g. Learning outcomes, assessment methods and key content stays unchanged. However, via course syllabus, it is possible to specify or change the course execution in each realization of the course, such as how the contact sessions are organized, assessment methods weighted or materials used.

LEARNING OUTCOMES

By the end of the course, students should be able to:

  • Understand what is an AI agent and what an AI can do
  • Understand how an AI agent may interact with the real world through user prompts as well as assess how it interacts with the physical world
  • Apply this knowledge to design a concept for an AI agent that takes into account the challenges due to complexity and unpredictability, and critically evaluate the concept

Credits: 3

Schedule: 29.04.2025 - 03.06.2025

Teacher in charge (valid for whole curriculum period):

Teacher in charge (applies in this implementation): Jens Schmidt, Tua Björklund, Siavash Haghighat Khajavi, Marko Nieminen, Severi Uusitalo, Christian Lindholm

Contact information for the course (applies in this implementation):

CEFR level (valid for whole curriculum period):

Language of instruction and studies (applies in this implementation):

Teaching language: English. Languages of study attainment: English

CONTENT, ASSESSMENT AND WORKLOAD

Content

  • valid for whole curriculum period:

    An AI agent is a program that can perform tasks autonomously on behalf of a user or another program. One critical question is how AI agents interact with the "real world", where the real world refers to both humans and the broader physical environment. From the perspective of the AI agent, the real world is a complex environment. This complexity imposes constraints on the extent to which the environment can be taken into account in designing AI agents that perform specific tasks.

    In this course we explore how AI agents can be designed to deal with the interface between code and the real world to reliably achieve desired goals. The course approaches this topic from two angles:

    • Students will develop an idea into a concept or prototype of an AI agent that interacts with the real world
    • Students will explore theoretical concepts by delving into the literature and interact with companies

    This course has been designed with a broad range of students in mind to get a mix of perspectives on designing and interacting with AI agents. Students will work in multidisciplinary teams.


Assessment Methods and Criteria

  • valid for whole curriculum period:

    Participation in mandatory lectures, participation in group work.

Workload

  • valid for whole curriculum period:

    Pre-readings, weekly lectures, group projects, individual assignment.

DETAILS

Substitutes for Courses
Prerequisites

FURTHER INFORMATION

Further Information

  • valid for whole curriculum period:

    Teaching Language: English

    Teaching Period: 2024-2025 Spring V

Rules of Conduct - Students´ Rights and Responsibilities (in force from 1 August 2020)

Aalto University Code of Academic Integrity and Handling Violations Thereof