Back to Tutorials
Tutorial 1 of 5

AI Fundamentals

Learn the basics of artificial intelligence, machine learning, and large language models.

15 min read
Reading
Progress20%

What is Artificial Intelligence?

Artificial Intelligence (AI) is the simulation of human intelligence by machines. Instead of following rigid rules, AI systems can learn from data, recognize patterns, and make decisions—much like humans do.

Think of AI as teaching a computer to think. While traditional programs follow exact instructions (if X, then do Y), AI can handle ambiguity and learn from examples.

Traditional Programming

"If the user types 'hello', respond with 'Hi there!'"

Exact rules, limited flexibility

AI Approach

"Understand greetings and respond naturally in context"

Learns patterns, handles variations

Machine Learning: How AI Learns

Machine Learning (ML) is a subset of AI where systems learn from data without being explicitly programmed. There are three main types:

1. Supervised Learning

Learning from labeled examples. Like a teacher showing correct answers.

Example: Showing the AI thousands of emails labeled "spam" or "not spam"

2. Unsupervised Learning

Finding patterns in data without labels. Discovering hidden structures.

Example: Grouping customers by behavior without predefined categories

3. Reinforcement Learning

Learning through trial and error with rewards. Like training a pet.

Example: An AI learning to play chess by winning and losing games

Large Language Models (LLMs)

Large Language Models are the technology powering modern AI assistants like ChatGPT, Claude, and the agents you'll build on NabkaAI. They're trained on vast amounts of text to understand and generate human-like language.

How LLMs Work

  1. 1

    Training

    The model reads billions of web pages, books, and documents to learn language patterns.

  2. 2

    Understanding Context

    When you send a message, the model analyzes it in context of the entire conversation.

  3. 3

    Generating Response

    The model predicts the most likely words to come next, one at a time, creating coherent responses.

Important Note

LLMs don't truly "understand" like humans—they're incredibly sophisticated pattern matchers. They can sometimes generate incorrect information confidently (called "hallucinations"). Always verify important facts!

The Art of Prompting

A prompt is the input you give to an AI. The quality of your prompt directly affects the quality of the response. This is why "prompt engineering" is such a valuable skill!

Good Prompting Principles

Be Specific

Vague

"Write about dogs"

Specific

"Write a 200-word guide on training a golden retriever puppy, focusing on house training"

Give Context

Tell the AI who it's talking to, what the goal is, and any constraints.

"You are a customer support agent for a software company. A user is frustrated because their login isn't working. Respond empathetically and provide clear troubleshooting steps."

Specify Format

Tell the AI how you want the response formatted.

"List 5 marketing ideas for a coffee shop. Format as a numbered list with a one-sentence description for each."

Key Takeaways

  • AI enables machines to learn from data and make intelligent decisions
  • LLMs are trained on massive text datasets to understand and generate language
  • Good prompts are specific, provide context, and specify the desired format
  • Always verify AI outputs—LLMs can make mistakes or "hallucinate"

Ready for the Next Step?

Now that you understand AI basics, let's dive into what AI agents are and how they work.