Self-paced

Explore our extensive collection of courses designed to help you master various subjects and skills. Whether you're a beginner or an advanced learner, there's something here for everyone.

Bootcamp

Learn live

Join us for our free workshops, webinars, and other events to learn more about our programs and get started on your journey to becoming a developer.

Upcoming live events

Learning library

For all the self-taught geeks out there, here is our content library with most of the learning materials we have produced throughout the years.

It makes sense to start learning by reading and watching videos about fundamentals and how things work.

Search from all Lessons


LoginGet Started
← Back to Lessons
Edit on Github

What Is A Prompt

What is a prompt?
  • What is a model?

Prompt

A prompt is the input data you give to the AI model to generate new content. It can be text, an image, a sound, or any type of data that the model is trained to understand.

Generative AI is a field of artificial intelligence that focuses on creating models that can generate new content based on a set of training data. It's like teaching a robot to paint; first, you show it thousands of paintings and then ask it to create its own artwork. In this way, all current generative AI models are trained on a large amount of data.

What is a prompt?

A prompt is the input data you give to the model to generate new content. It can be text, an image, a sound, or any type of data that the model is trained to understand. The prompt is the starting point for the model to generate an output based on the patterns it has learned from the training data.

For example, if you want to generate an image of a red apple, you would give the model a text prompt that says "red apple." The model will then use its knowledge from the training data to generate an image of a red apple based on the input prompt.

Each model or platform also has its own way of handling prompts; some models require specific formats or structures, while others are more flexible. It is important to understand how to create effective prompts to get the best results from the model.

What is a model?

A model in artificial intelligence is like a human brain, composed of a neural network that can understand some input data (the "prompt") and generate an output from it. Depending on the architecture and training data, the input data can be of different types. In the current revolution of generative AI, the most advanced models can understand and generate text, sound, images, videos, and any type of data you can imagine.

Here are some models and their input and output data in a table:

ModelInput DataOutput Data
DALL-E-3TextImages
GPT-4 OmniText, Images, audio (not yet available to the public)Text, images, and audio (as of writing, it only generates text; in the coming months, it will generate more)
MidJourneyText or imagesImages
Gemini UltraText, Audio, ImagesText

Prompt Engineer

Learning the concept of a prompt is fundamental to becoming a Prompt Engineer. A Prompt Engineer is someone who writes effective prompts to interact with an AI model and always achieve the same result. Or rather, the same result structure.

If you are a beginner, I recommend this article on what is Prompt Engineering. And if you want to delve a little deeper, I invite you to take our free Prompt Engineering course.

In summary, a prompt is the starting point for an AI model to generate new content. Learning to create effective prompts is essential to get the best results from generative AI.