FlexStack: Python AI Principles 1 - Large Language Models

  • Overview
  • Course Content
  • Requirements & Materials
Overview

FlexStack: Python AI Principles 1 - Large Language Models

Course Description

This course provides a practical on-ramp to modern artificial intelligence. Through a mix of instructor-led demonstrations, class exercises, and knowledge checks, individuals with basic Python experience will be able to solidify foundational coding skills and better understand AI applications. Participants will learn when to use rules, classical Machine Learning (ML), or Large Language Models (LLMs). The instructor will also guide learners through how tokens, context windows, embeddings, and cost/latency trade-offs shape design, and how to write robust prompts with schemas and failure checks. It is the first of three courses that make up the FlexStack: Python AI Principles Certificate.

Course Content

FOUNDATIONS 

  • Modern AI Landscape and Use Cases
  • Rules Versus Classical Machine Learning (ML) Versus Large Language Models (LLMs)
  • Tokens, Context Windows, Latency, and Cost 

PRACTICE 

  • Prompting with Schemas and Few-Shot Patterns
  • Text Baselines with Term Frequency-Inverse Document Frequency (TF-IDF) and Linear Models 

OPERATIONS 

  • Retrieval-Augmented Generation (RAG) with Grounded Citations and Abstain Rules
  • Evaluation, Leakage Controls, and Guardrails 

Exercises and demonstrations build TF-IDF baselines, RAG basics with citations, and sound evaluation (splits, leakage control, Precision-Recall Area Under the Curve/Mean Absolute Error (PR-AUC/MAE)). We will cover risks (privacy, bias, prompt injection), add guardrails and Human in the Loop (HITL), as well as make work reproducible and adherent to a fixed budget.

Requirements & Materials

Requirements

A Windows or Mac laptop with a webcam is required to participate in the course. Tablets or other devices are not supported. Recommended: Additional monitor. 

Familiarity with using a computer and adequate typing ability. 

Course registration requires an approved application and advisor meeting. 

Participants are expected to have their cameras on during the interactive sessions and must attend 80% of the sessions to pass the course.

Prerequisites

Required:

Successful completion of the FlexStack: Python Fundamentals Certificate or evidence of equivalent skills.    

Recommended:

  • Working knowledge of Python, including functions, modules, and virtual environments
  • Basic data handling with numpy and pandas, including reading Comma-Separated Values/JavaScript Object Notation (CSV/JSON) and simple joins or filters
  • Comfort with the command line and installing packages with pip
  • Introductory statistics and algebra, including means, variance, and simple probability
  • Ability to use an Integrated Development Environment (IDE)–Jupyter or VS Code–for notebooks and script

Materials

Provided:

  • Canvas
  • Vocareum
  • H5P
  • Lecture Materials

Who Should Attend

This course is designed for technical professionals with working knowledge of Python. It is ideal for data and operations analysts, product and program managers, educators, Information Technology (IT) generalists, and technical leads who want to learn how to select and deploy practical, auditable solutions.

Man who is a technical lead stands in front of screen with Python code as part of the FlexStack: Python AI Principles Certificate.

What You Will Learn

  • How to distinguish rules, classical machine learning, and Large Language Models (LLMs)
  • Basics of tokens, context windows, and cost trade-offs
  • How to write robust prompts with schemas and failure checks
  • How to build term frequency-inverse documents and frequency baselines for common text tasks
  • Implementation of light retrieval-augmented generation (RAG) with grounded citations
  • Application of sound evaluation and leakage controls
  • How to add guardrails, human in the loop, and reproducibility
Woman sits in front of three monitors reviewing Python code with her male coworker for the FlexStack in Python AI Principles Certificate.

How You Will Benefit

  • Make defensible build versus buy decisions by choosing between rules, classical machine learning, and Large Language Models (LLMs) for specific tasks.
  • Establish strong baselines and retrieval-augmented generation (RAG) prototypes that show measurable value with grounded citations.
  • Evaluate models credibly using proper splits, leakage checks, and task appropriate metrics.
  • Reduce risk with guardrails, privacy practices, and human in the loop checkpoints.
  • Communicate cost, latency, and quality tradeoffs clearly to stakeholders.
  • Improve team speed through reproducible configs, seeds, and runbooks.

Want to learn more about this course?