JOSEPH_G
Course overview

Data & Prompting

Move from model mechanics into model behavior. This course explains why data quality, tokenization, and prompting shape the answers people actually receive.

track Foundations
lessons 2
time 30 min
level Beginner
Your progress
0 of 2 lessons complete

Progress loads on this device after the page opens.

Start courseCourse overview
What this course does

A practical beginner course on the inputs that shape model behavior, written to help readers judge output quality instead of trusting fluency.

Back to full catalog Start with lesson 1
Course map

Move through the course in order.

2 lessons · 30 min
Phase 1

Phase 1. Behavioral inputs

Study the practical forces that shape output quality before a model ever answers the user.

2 lessons · 30 min
  1. 1
    Why Some Words Are Easy for AI and Others Are Hard

    AI does not see words the way humans do. Some words split into clean, simple pieces, while others break into many small parts. In this lesson, we explore why tokenization is uneven and why that affects how models process language.

    15 min · Core lesson
    Next
  2. 2
    Garbage In, Fluent Garbage Out

    A language model learns from patterns in its training data. If that data is messy, biased, outdated, or low quality, the model can produce answers that sound good but are still wrong. In this lesson, we explore why data quality matters more than most people think.

    15 min · Core lesson
    Open