Learning center
How AI works
Large language models, embeddings, RAG, AI agents: how AI produces its answers.
What is a large language model (LLM)?
A large language model (LLM) is an AI model that learns how words fit together from huge amounts of text and writes by predicting what comes next.
What are embeddings?
Embeddings represent the meaning of text or images as lists of numbers (vectors), so software can find related content even when the wording differs.
What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation (RAG) has AI search relevant documents before it answers and base its reply on what it finds, so answers can cite sources.
What is an AI agent?
An AI agent is a system where a large language model plans steps, uses tools, and checks results to reach a goal. The key is deciding where people step in.
What is speech recognition?
Speech recognition is technology that lets a computer turn spoken words into text. Knowing how it works helps you get more out of dictation and transcripts.
What is text-to-speech?
Text-to-speech is technology that lets a computer read written text aloud. Knowing how it works helps you use read-aloud and voice messages with confidence.
What is a prompt?
A prompt is the text you give an AI: your request plus any background, sources and examples. Clear goals and conditions get you closer to the answer you need.
Hand off one thing and see
All you need is an email address. Start on the Free plan by saying hello to muku.