Modern AI applications do not rely on language models alone as their source of knowledge. They often combine prompts, search systems, external data sources and evaluation methods to find, generate and use information.
This course introduces large language models, AI-based information search, query and prompt design, and retrieval-augmented generation from both theoretical and practical information-use perspectives. Students learn how AI tools use information sources behind generated answers, and how to evaluate whether the results are relevant, reliable and effective.
Course contents
- Information search and AI: finding, evaluating and using digital information, including relevance and reliability
- Matching and generation: how search engines retrieve results and language models generate responses
- Lexical vs. semantic search: keyword-based vs. meaning-based approaches
- Large language models: basic principles, capabilities and limitations
- Query and prompt design: creating effective searches and prompts
- Retrieval-augmented generation (RAG): combining external data with generative models
- Evaluation: assessing relevance, reliability and effectiveness
Learning outcomes
Sudents will learn how modern search and generative AI systems work, how to formulate better queries and prompts, how retrieval can improve AI-generated answers, and how to evaluate whether the results are useful, reliable and relevant.
The course is suitable for learners who want to understand and use AI tools more systematically, whether for studies, work or professional development.
Course material
The lectures and other course materials are provided as recordings and online materials in Moodle.
Students can study the main content flexibly through the learning environment, where the teacher will also provide instructions for assignments and course activities. The exercises are designed to support conceptual understanding.
Students analyse using a laboratory environment, how information search, language models, prompts and generated answers work. The tasks include practical examples and reflective exercises that help students connect technical ideas with real information-use situations.
Teaching schedule
The course can be completed independently through Moodle materials, recordings and assignments. Optional online meetings are held weekly on Fridays at 11:15–13:00.
Exercise deadlines are scheduled bi-weekly throughout the course.
Completion methods
The course is completed by successfully completing a series of scheduled individual assignments. The assignments are completed independently according to the course timetable and gradually develop the knowledge and skills covered during the course. There is no final examination.
More information in the Tampere University study guide.
You can get a digital badge after completing this course.