This course explores how AI — particularly large language models and agentic systems — is transforming software engineering practice. Students learn to use, evaluate, and reason critically about AI-augmented development tools, from prompt engineering and retrieval-augmented generation to autonomous coding agents and multi-agent orchestration. The course blends conceptual foundations with hands-on projects.
Schedule
| # | Topic | Slides |
|---|---|---|
| 1 | Introduction | |
| 2 | LLMs and their Application in Software Engineering | |
| 3 | Prompt Engineering in Software Engineering | |
| 4 | RAG-Based Prompting | |
| Retrieval-Augmented Generation (Deep Dive) | ||
| 5 | Building a CLI Agent | |
| 6 | Agentic AI Design Patterns | |
| 7 | Towards a “Personalized” AI Assistant | |
| 8 | AI Agent Orchestration | |
| 9 | Agentic Protocols |
Tools
Paper Reviews
-
Large Language Model-Based Agents for Software Engineering: A Survey Junwei Liu et al. [ArXiv]
-
Promptware Engineering: Software Engineering for Prompt-Enabled Systems TOSEM 2026 [ArXiv]
-
From Issues to Insights: RAG-based Explanation Generation from Software Engineering Artifacts Pöttgen et al. · NLBSE 2026 [ArXiv]
-
Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges SANER 2026 [ArXiv]
-
On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub TOSEM 2026 [ArXiv]
-
Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution Under Review — ICLR 2026 Workshop on MALGAI [OpenReview]
Resources
- Stanford CS146S: The Modern Software Developer
- CMU 17-316/616: AI Tools for Software Development
- USU DATA5570: Building Software With Artificial Intelligence
- A Whole New World — Annie Vella on AI-native development
- Wikipedia: AI-assisted software development
- IBM: AI in software development
- Prompting Guide
- Model Context Protocol