ITCS 5010

Topics in Computer Science: Evaluation of Agentic AI Systems

3credits
About this course

Topics in computer science selected to supplement the regular course offerings. A student may register for multiple sections of the course with different topics in the same semester or in different semesters. Section information text: This is a project-driven course on building applications with generative AI foundation models. There are no exams. Students complete one or two programming assignments, two or three mini-projects, and a final group project. Students begin by building intuition for large language models (LLMs) through prompt and context engineering, working with model APIs, and applying models to tasks such as summarization, structured extraction, and code generation. They then study how these models work and how to ground them in external knowledge through Retrieval-Augmented Generation (RAG). From there, the course moves to agentic AI: designing agents that plan, use tools, and act over multiple steps. Students connect agents to external tools and data through the Model Context Protocol (MCP), coordinate multiple agents with the Agent-to-Agent (A2A) protocol, and practice harness engineering, the work of building the loops, memory, guardrails, and evaluation pipelines that make agents reliable in production. A central part of the course is industry-grade project work drawn from our corporate partnerships with companies such as Honeywell, which gives students hands-on experience with real-world problems and current industry practice. A background in machine learning is helpful but not required.

All available terms

18 terms

Avg. GPA
3.83
Grades
201

Other grades

W1.5%
More course details

University of North Carolina, Charlotte

ITCS 5010 at UNC Charlotte: average GPA 3.83 across 201 students. Grade distribution by term. Topics in computer science selected to supplement the regular…

Average GPA: 3.83

Grade distribution records: 201 students across 18 terms.

Grade distribution

GradeStudentsPercent
A16381.1%
B2311.4%
C52.5%
W31.5%

Based on 201 student grade records across 18 terms and 14 professors.

Instructors

Related courses

The course page is taking longer to load. This summary is still available.

We could not load the full course details. This summary is still available.

Still loading. This can take a moment on a slow connection.

Loading My Class Grades