Gen-AI / LLM Programming course

This course focuses on practical programming with generative AI and large language models (LLMs), emphasizing application design, software integration, and real-world use cases. Students learn to build LLM-powered applications by calling cloud-based LLM APIs using the LangChain orchestration framework, programming in Python. Designed for students interested in applied computer science and software development rather than machine learning research. Prior object-oriented programming experience in Python is required. One way to get this prior experience is to take our Foundations in Python & Machine Learning course, however, this is not required as a prerequisite.

This course is equal to a bit more than a full semester of school instruction.

What your student will learn:

• Using the LangChain framework in Python to make calls to cloud-based LLM APIs
  • Using LangChain to manage LLM prompting and prompt histories
  • Classic prompt strategies covered and use of prompt repositories
• Using Retrieval Augmented Generation (RAG) in order to search and utilize private data not present in LLM model trained knowledge 
  
  • Employing vector databases as part of RAG
  • Covering RAG best practices and design patterns to improve RAG effectiveness 
  • Querying unstructured documents via RAG such as PDFs, etc.
  • Interfacing LLMs with structured data(bases) including SQL and NoSQL or key-value stores, including schema definition using Pydantic
•  LLM Tool Calling and Agentic Workflows
  • Covering the ability of LLM's to call other software functions, programs, and tools formally, augmenting their capability with vetted tools  
  • Introduction to agents and how these have evolved into cyclic graphical methods
  • Introduction to LangGraph as a formal way of building agentic control flows
•  Using Model Context Protocol to enable standardized two-way connections between important data sources and AI-powered tools

This course is given over the 4 month semester during the school year, with weekend-only and mid-week class times available. Typically weekly time commitment is 10-12 hours. 3-month accelerated cohorts available in summer months. All classes are conducted via Zoom with a live, synchronous instructor. 

Tuition is $3996 for the full semester course

Why take this course? 

The remarkable recent developments in frontier Generative-AI LLMs have led to a new way of programming AI applications where the raw intelligence of LLM models from OpenAI, Anthropic, Google, etc., is tapped into via cloud API LLM calls, and application workflows are managed in languages like Python or JavaScript.

There are many frameworks emerging to manage LLM usage, but LangChain has become a leading framework for prototyping and building such AI-applications.  This exciting new area of using LLMs to build custom AI applications beyond Chat-bots is a rapidly evolving programming domain that is exploding—and at times somewhat chaotic—it is evolving so quickly. Fortunately, it is accessible to students in high school and even middle school who have solid Python OOP mastery and a willingness to learn tooling such as LangChain and LangGraph and new protocols such as MCP (Model Context Protocol) as they develop.

AI researcher and thought leader Andrej Karpathy famously labelled predictive machine learning "Software 2.0", and he calls this type of LLM programming "Software 3.0", describing it as a new kind of computer of the future

There will be many opportunities for students willing to ride this exciting new wave of programming—opportunities to build unique applications, seek corporate internships, build passion projects suitable to assist in college admissions, perform research in numerous sociocultural fields, and even found startup companies at a very early age. 

This course provides a structured way to learn this new and rapidly developing area as it emerges, even for relatively new programmers at an early age. This is one of the most sought after software skills right now in tech companies and industry in general. Learning this emerging area is is a great way to build solid Python object-oriented programming skills, as well as build a GitHub portfolio of exciting applications. Don't miss this wave of opportunity if your student is interested in software application development, or even using it for scientific inquiry as an alternate STEM usage that is complementary to traditional predictive machine learning.