CSC465 Agentic AI

[3–0, 3 cr.]

This course focuses on the design and implementation of agentic AI systems capable of reasoning, planning, and executing multi-step tasks autonomously. Students gain hands-on experience building agentic pipelines using contemporary frameworks and APIs. Topics include prompt engineering techniques (zero-shot, few- shot, chain-of- thought, and tree-of-thought prompting), ReAct loops (reasoning and acting), tool use and function calling, memory architectures (short-term and long-term), planning strategies, multi-agent orchestration, retrieval- augmented generation (RAG), agent evaluation and benchmarking, safety and alignment considerations in autonomous systems, and human-in-the-loop design patterns.

Prerequisite: CSC245