Syllabus

Agentic Artificial Intelligence: Design, Implementation, and Orchestration

Course Description

This course explores the emerging paradigm of Agentic Artificial Intelligence: AI systems capable of reasoning, planning, and acting autonomously through structured protocols and external tool integration. Students will learn to design, implement, and deploy Model-Context-Protocol (MCP)-based agent systems, integrate multiple models and APIs, and evaluate their ethical, cognitive, and computational implications.

The course emphasizes applied construction and reflective practice over rote theory. Students will build containerized agent workflows, practice context and protocol design, and engage in iterative fail-and-survive learning cycles to develop robust technical and critical thinking skills.

Learning Objectives

Course Student Learning Outcomes (CSLO)

1. Explain the principles of rational and cognitive agents.
2. Implement autonomous behaviors using Model-Context-Protocol design.
3. Compose multi-agent systems that integrate APIs and external tools.
4. Deploy and evaluate agent systems in reproducible computing environments.
5. Communicate design choices and ethical reasoning clearly.

Required Learning Materials:

There is no textbook requirement for this course. Relevant reading materials will be uploaded to LMS.

Assessments and Grading:

Method of Evaluation

Assessment	% of Final Grade	CSLO
Reading Reflection	30%	1,5
Labs	10%	1,2,3,4,5
Midterm Exam	20%	1,2,3,5
Final Project	40%	1,2,3,4,5

Grade Scale:

Grade	Quality Points	Numeric	Interpretation

D grades are not used. Refer to the Graduate Catalog for description of NG (No Grade), W, & other grades.

Assessments:

• Reading Reflections: Students critically synthesize foundational readings. This assesses conceptual understanding and their ability to communicate ideas clearly.
• Weekly Labs: Students prototype, fail, analyze, and rebuild various frameworks in each lab.
• Midterm Exam: Evaluates conceptual reasoning and short design analysis questions.
• Final Project: A larger project that comprehensively assesses students’ understanding of the course materials.

Lateness Policy:

Labs/Project milestones that are late are assessed a 10% per day late penalty. Saturday and Sunday are each days.

Course Topics and Schedules

Week	Topic
1	From Symbolic AI to Agentic AI
2	Rational Agent and Environments
3	Cognitive Architectures and LLM Integration
4	From Prompting to Protocols
5	Context Engineering
6	The Protocol Layer
7	Multi-Agent Design Patterns
8	Communication and Coordination
9	Model Selection and Hybrid Intelligence
10	Agent Infrastructure and Deployment
11	Agent Evaluation and Benchmarking
12	Applications of Agentic AI
13	Safety, Ethics, and Human Oversight
14	Final Project Development Update
15	Final Project Reflection