The PlainLogic blog
AI explained in plain logic
Short, practical AI explainers in plain words, each linked to a hands-on experiment. No hype, no jargon, no account needed.
All guides
Eight guides, zero jargon
Read them in any order. Each one ends with a button that takes you to the matching experiment.
What is an LLM?
An LLM learns patterns in text and uses context to predict the next token.
Read the guide →What are tokens?
Tokens are the pieces a language model reads and writes.
Read the guide →What is RAG?
RAG finds relevant source material before an AI writes an answer.
Read the guide →What are embeddings?
An embedding represents something as a list of numbers so it can be compared.
Read the guide →AI agent vs chatbot
A chatbot is a conversation interface. An agent can also take steps toward a goal.
Read the guide →When should you NOT use AI?
Use plain rules when the right answer follows a clear, testable rule.
Read the guide →Why AI hallucinates
AI can produce convincing text that is unsupported or wrong.
Read the guide →How to write a clear prompt
A useful prompt explains the task, context, constraints, and desired format.
Read the guide →Every guide pairs with a hands-on experiment. The demos are simplified educational visualizations — they illustrate concepts, not real model internals.