The best way to understand how AI works is to think about how you learn. AI systems learn in a similar way: by being given lots of information (data) and then finding patterns and relationships within that data.

AI often learns through a process called Machine Learning, which has three main parts:

An illustrated image of a female chef in a white uniform, red scarf, and a tall white hat. She's holding a whisk in her right hand and gesturing with her left, surrounded by floating recipe scrolls, musical notes, and fresh ingredients like tomatoes, garlic, onions, basil, and carrots.

1. Data

AI models learn from data. This data can be anything—pictures, text, sounds, or numbers. The more high-quality data an AI model is given, the more information it has to learn from. Think of it this way: a chef that has learned to cook by tasting thousands of different ingredients and recipes likely has a more refined palette. To stay up-to-date and accurate, AI models often need to be fed new data over time.

An illustrated image of a boy sitting at a desk, looking at a computer screen. The screen displays six images of dogs and cats. The boy points at the screen while a network of lines connects to smaller floating images of animals above the monitor, suggesting a training process. A lightbulb is lit up to the right of the network.

2. Training

After we collect the data, the AI model is trained on it. This is a lot like a student studying for a test. The AI is given the data and an objective (for example, “find the difference between a dog and a cat”). It runs through the data over and over again, making adjustments and getting better with each try until it can accurately complete the task.

An illustrated image of a hand holding a smartphone. The screen displays a person's smiling face with a digital square around it. A chat bubble points to the person and says "New Friend". At the top of the screen, a brain icon with connecting lines symbolizes a digital process.

3. Inference

Once the AI model is trained, it’s ready to be tested on new data! When you start taking picture of a new friend and your phone uses what it learned about facial recognition to correctly tag them, that’s known as inference. The AI is using its knowledge to make a real-time prediction or decision on something it hasn’t seen before.