Artificial Intelligence as a Challenge for PSaPA 1600-SZD-SPEC-SI-PA
The course provides a comprehensive overview of the theoretical and practical aspects of creating prompts for artificial intelligence systems. It covers the fundamentals of prompt engineering, including the definition of prompts and their critical role in AI-driven content generation, as well as techniques and concepts for designing effective prompts. Participants will analyze popular AI content generators such as ChatGPT, Gemini, and Copilot, exploring the differences between generators and prompts and their interdependencies. The course emphasizes the creation and optimization of prompts, focusing on personalizing and tailoring them to specific needs, managing priorities, and analyzing examples of educational, research-focused, and creative prompts with practical applications. It also delves into the use of AI in fields like education, marketing, data analysis, and coding, addressing advanced features such as context understanding and result personalization. Through practical exercises and brainstorming sessions, participants will design prompts for diverse categories, test responses on various AI platforms, and optimize their outputs. Ethical and technical aspects are also highlighted, providing guidelines for responsible and high-quality prompt creation. The objective is to equip participants with the skills to craft precise and efficient prompts, maximizing the potential of AI models in their academic, educational, and professional activities.
Course coordinators
Learning outcomes
Knowledge | The graduate knows and understands:
WG_01 - to the extent necessary for existing paradigms to be revised - a worldwide body of work, covering theoretical foundations as well as general and selected specific issues - relevant to a particular discipline
within the social sciences
WG_02 - the main development trends in the disciplines of the social sciences in which the education is provided
WG_03 - scientific research methodology in the field of the social sciences
WK_01 - fundamental dilemmas of modern civilisation from the perspective of the social sciences
Skills | The graduate is able to:
UK_05 - speaking a foreign language at B2 level of the Common European Framework of Reference for Languages using the professional terminology specific to the discipline within the social sciences, to the extent enabling participation in an international scientific and professional environment
Social competences | The graduate is ready to
KO_01 - fulfilling the social obligations of researchers and creators
KO_02 - fulfilling social obligations and taking actions in the public interest, in particular in initiating actions in the public interest
KO_03 - think and acting in an entrepreneurial manner
Assessment criteria
1. Description of requirements related to participation in classes, including the
permitted number of explained absences: Prerequisites include a basic understanding of artificial intelligence (AI) concepts and general familiarity with digital and technological tools, as well as proficiency in computer use, including basic experience with web applications and working in online environments. Participant responsibilities involve active participation in classes, including practical workshops and individual exercises, systematic completion of tasks such as homework related to creating and testing prompts, and engagement in discussions and teamwork. Assessment and completion require attendance at a minimum of 75% of practical sessions, with mandatory submission of a final project consisting of a set of designed and tested prompts. Participants are allowed a maximum of two excused absences, which must be justified with a medical certificate or other formal document. In the case of more than two absences, participants are required to make up for missed material within an agreed timeframe and complete additional tasks to address any deficiencies.
2. Principles for passing the classes and the subject (including resit session): The basic requirements for completing the course include active participation in classes, where participants must engage actively in workshops and individual exercises, and the completion of ongoing tasks, with systematic and timely execution of practical assignments and projects outlined in the course program. Attendance is mandatory for at least 75% of the sessions; in case of absences, participants are required to catch up on the material and provide valid excuses. The final project is a crucial component for course completion and involves designing and presenting a set of prompts tailored to specific AI applications (e.g., education, marketing, coding). The project will be evaluated based on the quality, innovativeness, and effectiveness of the designed prompts.
3. Methods for the verification of learning outcomes: Practical workshops: Participants' activity and the quality of their work during workshops are assessed. Tasks involve creating prompts for various applications (educational, creative, business-related) and testing them in environments such as OpenAI Playground or ChatBot. Final project: Each participant prepares a set of prompts for a selected application. The project must be supported by documentation that includes the objectives and assumptions of the prompts, an analysis of the results generated by AI, and optimization proposals based on the obtained outcomes. The evaluation focuses on the innovativeness, relevance, and practicality of the created prompts.
4. Evaluation criteria: Grading scale and evaluation criteria:5.0 (Excellent): Outstanding execution of the final project, innovative approach to prompt creation, full engagement in classes.4.5 (Very Good): High-quality final project, active participation in most classes, minor shortcomings.4.0 (Good): Final project meeting basic requirements, participation aligned with course regulations, limited involvement in additional exercises.3.5 (Satisfactory Plus): Adequate completion of the final project with significant gaps or deficiencies, minimal engagement in exercises.3.0 (Satisfactory): Final project at a basic level, minimal fulfillment of activity requirements.2.0 (Fail): Absence of a final project or failure to meet minimum standards, insufficient attendance and engagement.
Bibliography
Alammar, J. (2018). The Illustrated Transformer.Bengio, Y., Courville, A., Goodfellow, I. (2016). Deep Learning. MIT Press.Brown, T., et al. (2020). Language Models are Few-Shot Learners. NeurIPS.ChatGPT Prompting Guide – https://help.openai.com/en/articles/creating-effective-prompts OpenAI Playground Documentation – https://platform.openai.com/playground/chatOpenAI. (2023). Using GPT Models for Natural Language Processing. OpenAI Documentation.Russell, S., Norvig, P. (2020). Artificial Intelligence: A Modern Approach. Pearson.Tamkin, A., et al. (2021). Understanding Prompt Engineering. Stanford University.Zhai, X., et al. (2021). Multimodal Prompting in AI Systems. Nature Communications
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: