OMSCS Seminar: Agentic AI Essentials

  • Overview
  • Course Content
  • Requirements & Materials
Overview

OMSCS Seminar: Agentic AI Essentials

Course Description

Agentic AI marks the next evolution beyond traditional chatbots and LLM-based assistants, enabling AI systems to reason, plan, act, and learn autonomously. Unlike standard LLMs that passively respond to inputs, Agentic AI follows a four-step process: It perceives information from multiple sources, reasons through complex tasks, executes plans, and improves through feedback. This seminar is organized as a series of modules, each consisting of lectures, notebooks, write-ups, and discussions. Students will gain hands-on experience in prompt engineering, large language models (LLMs), retrieval-augmented generation (RAG), and ReAct (Reasoning and Acting) frameworks to build interactive, scalable AI solutions using pre-trained models.

Course Content
  • Module 4.1 Workshops Overview: Access to four NVIDIA-sponsored workshops. While entirely optional, they provide valuable hands-on experience with cutting-edge agentic AI development tools and concepts.
  • Module 4.1.1 Building LLM Applications with Prompt Engineering (PRMPT): Learn to apply iterative prompt engineering best practices to solve language-related tasks. Use LangChain with Llama-3.1 NIM models to build LLM workflows for document analysis, generation, and chatbot interactions.
  • Module 4.1.2 Rapid Application Development with LLMs (RAD): Explore the LLM ecosystem including encoder and decoder models from HuggingFace. Build apps using semantic search, embeddings, classification, and generative pipelines. Orchestrate workflows using LangGraph and LangChain.
  • Module 4.1.3 Building RAG Agents with LLMs (RAG): Implement RAG agents capable of document reasoning and stateful interaction. Learn dialog management, embedding-based retrieval, guardrailing, and deploying modular LLM pipelines.
  • Module 4.1.4 Building Agentic AI Applications with LLMs (AAI): Design agent systems that integrate reasoning, tool use, and multi-agent orchestration. Create structured outputs; interface with APIs; and manage resilient, concurrent workflows using LangGraph and software engineering best practices.
Requirements & Materials

Prerequisites

RECOMMENDED:

Jupyter Notebook: Recommended but not mandatory


REQUIRED:

Python: beginner level

Materials

PROVIDED (Student will receive): 

All content is available in Canvas.

Session Details

Who Should Attend

This seminar is designed for OMSCS students and alumni curious about building AI agents that go beyond simple prompting or chatbot responses. It is ideal for learners interested in exploring agentic AI; no prior deep learning experience is required.

Computer science students coding on computers

What You Will Learn

  • An introduction in applying prompt engineering techniques to build generative, analytical, and conversational LLM applications using popular frameworks
  • The core principles of Agentic AI and how it differs from traditional LLM-based assistants
  • Hands-on skills in prompt engineering and retrieval-augmented generation (RAG)
  • Integration of pretrained large language models (LLMs) into multi-step agentic workflow
Female professional in computer science lab looking at tablet

How You Will Benefit

  • Learn how to design and implement Retrieval-Augmented Generation (RAG) agents capable of document reasoning,
    stateful dialog, and structured outputs.
  • Become familiar with orchestrating agentic AI systems using popular tools to support concurrent, multi-step execution of tasks with integrated tool use.
  • Reflect critically on the limitations, opportunities, and broader implications of deploying agent-based AI in real-world contexts through structured learning reflections and peer dialogue.
  • Grow Your Professional Network icon
    Grow Your Professional Network
  • Taught by Experts in the Field icon
    Taught by Experts in the Field

TRAIN AT YOUR LOCATION

We enable employers to provide specialized, on-location training on their own timetables. Our world-renowned experts can create unique content that meets your employees' specific needs. We also have the ability to deliver courses via web conferencing or on-demand online videos. For 15 or more students, it is more cost-effective for us to come to you.

  • Save Money
  • Flexible Schedule
  • Group Training
  • Customize Content
  • On-Site Training
  • Earn a Certificate
Learn More

Want to learn more about this course?