Agentic AI Courses
Data Science Consulting
James Beeson headshot

James Beeson Team Leader / Curriculum Design Data Science & Educator

Ethan Saline headshot

Ethan Saline Website / Course Developer Data Scientist / ML Engineer

Wil Jones headshot

Wil Jones Website / Course Developer Data Scientist

Ian Blad headshot

Ian Blad Course Developer I/O Psych Major

Kimberly Juarez headshot

Kimberly Juarez Course Developer Data Scientist

Camila Ramirez headshot

Camila Ramirez Course Developer Data Scientist

Deliverables
01
DS Society Bootcamp Curriculum with Website
02
Special Topics Curriculum with Website
03
Additional Teaching Resources - instructor notes, grading schema, etc.

Course Objectives

  • Be able to plan, program, measure, test, and iteratively refine Agentic AI solutions.
  • Know which problems are best solved with Agentic AI and when it is appropriate to do so.
  • Define Agentic AI and related concepts.
  • Grow an ability to self-learn in an ever-changing AI landscape.

Course Structure

Units and Capstone Overview

Unit 1

- Build -

Tools and Agents

  • Connect LLMs to tools and MCP
  • ReAct agent framework
  • Python (LangChain)

Unit 2

- Test -

Diagnostics

Use diagnostic systems (LangSmith) to:

  • Analyze traces
  • Create numeric measures
  • Create test cases (Golden datasets)
  • Perform A/B testing against test cases

Unit 3

- Refine -

Context Engineering

Refine agents using:

  • Deliberate architecture planning
  • Context offloading (file system, RAG)
  • Subagent orchestration
  • Sandboxing

Capstone

- Prove -

Battle of the Bots

  • Student-made agents go head to head in a competition

Course Contribution

  • Students update or adjust the curriculum to current AI standards