Welcome to AI Supported Software Development SoSe 2026! 👋

Aalen University of Applied Sciences Bachelor Program in Computer Science

How to use this site

The course material has three layers, and each has a job.

📚 Lectures. The lecture notes are the textbook of this course. Each one is self-contained, includes all external references, and goes into more depth than we have time for in the lecture room. Read them when you want the full picture of a topic, or when you want to follow up on something that was only briefly mentioned in class.

🖼️ Slides. The slides are what we actually used during the lecture. Slide headings link back into the corresponding lecture notes, so the slides double as a map into the deeper material. Use them to recall what was covered in class, and click through to the lecture when you want the longer explanation.

✅ Exercises. The exercises are your self-assessment. They are the feedback loop that tells you whether the material has actually stuck. Once you can solve them comfortably, you are prepared for the exam. If an exercise feels hard, that is a signal to go back to the corresponding lecture section.

Materials are uploaded shortly after each class session, typically within 24 hours.

Learning Content

• Positioning the role of generative AI in modern software engineering processes (e.g., for code, tests, requirements, documentation)
• Fundamental concepts of AI-assisted development tools (including language models, context windows, inference behavior, hallucinations)
• Principles for designing interactions with AI systems (prompting strategies, system instructions, examples, context control)
• Architecture and integration of AI-assisted assistants and agent-based approaches into existing development environments and processes
• Methods for the structured generation and further processing of AI outputs (e.g., formalized formats, validation, integration with tools and pipelines)
• Approaches to quality assessment and trust-building for AI-generated software artifacts, and how to embed them into existing quality assurance processes
• Methods to observe and measure acceleration, productivity changes, and impacts on maintainability in software development projects
• Common failure modes, risks, and attack vectors of AI-assisted development tools, as well as basic protection and governance mechanisms
• Organizational and economic conditions/frameworks for using generative AI in software engineering