What is artificial intelligence?

AI is a toolbox of methods that help computers solve tasks. At Luna Workshop we want to choose the right tool before choosing a model.

You can follow this course without an account or programming. Examples use synthetic data and AI outcomes need checking.

How it works, step by step

AI is not one kind of model

Artificial intelligence is a family of methods for recognition, prediction, planning and generation. A rule-based system follows instructions written by people. Machine learning learns relationships from examples; deep learning uses networks with many layers. Generative AI produces new content. An LLM works with language, but product recommendations or defect detection may use other models. Think of a toolbox: choose a tool for the problem. A simple algorithm can be more suitable than an agent for a fixed rule.

How learning changes a model

Training data is the set of examples used to adjust model parameters. Supervised learning includes a target, such as “spam”. Unsupervised learning finds structure, such as customer groups. Self-supervised learning creates targets from data, for example predicting following text. Validation helps choose settings; the test set stays separate until final evaluation. A model that memorizes examples and fails on new data is overfitting. A proper split prevents information from the test set leaking into training.

From tokens to an answer

A token is a unit of text: sometimes a word, sometimes a word fragment or punctuation. The model processes context tokens and estimates a distribution over the next token. Selection repeats until stopping. Transformer attention combines information about relationships between tokens; it is not human attention. Training changes parameters, while inference uses the trained model. An answer can sound coherent without being true: generating text does not independently verify facts.

The visual map

Follow the solid arrows for the main flow. Dashed blue arrows supply data or context; dashed pink arrows show feedback or returning results. Colors and shapes distinguish models, stores, decisions and outputs. On smaller screens, scroll horizontally to follow the entire diagram.

A complete example

A calculator adds prices using rules. A spam filter learns from examples. An LLM writes descriptions. Vision detects defects; a recommender ranks products. A robot combines perception and action.

Try it yourself

1. Group these examples: calculator, spam filter, chatbot, OCR, recommendations, robot, forecast and translation.
2. Record the input, source and expected outcome before running the experiment. Use only the fictional data in the example.
3. Follow the diagram stages. At every step record what information is received and produced; do not confuse intermediate output with the final outcome.
4. Repeat after removing necessary information or making the input ambiguous. Check whether the system clarifies, stops or invents an answer.
5. Compare with the explained solution. Keep the configuration, date, result and an explanation for differences. Change one thing and retest.

An explained solution

Fixed arithmetic uses rules; classification learns; writing generates. Not all need an LLM or agent. A successful exercise lets you show the connection between input, stages and outcome. When information is missing, a cautious answer is more useful than invented details. Compare more than style: check conditions, sources and operations too.

When it helps and what can go wrong

A chat interface does not identify the technology behind it. Choose this approach when it improves a measured need. Keep a simple baseline and compare outcomes using identical inputs. One successful example does not establish reliability in every situation.

Check your understanding

Is every automation AI?

No. A fixed rule can automate something without learning or flexible reasoning.

Why not evaluate only on training data?

We want performance on new situations, not proof of memorization.

What outcome should this exercise produce?

Fixed arithmetic uses rules; classification learns; writing generates. Not all need an LLM or agent.

Words to remember

• AI: A family of methods, not a synonym for chatbot.
• Overfitting: The model fits the examples it has seen too closely.
• Token: A unit used by the model for text and context limits.

Sources and your next step

• Hugging Face — LLM Course
• scikit-learn — User guide

To prepare: no previous courses required.

Continue with: F02 — How does a machine learn? · F06 — Chatbot, assistant, agent and agentic system