Glossary

AI Glossary

Plain-English definitions of the AI terms behind modern assistants — what they mean and how they apply to MiyoMind.

What is an AI assistant?

An AI assistant is software that understands natural language and completes tasks for you. Learn how modern LLM-based AI assistants work and fit in.

What is a large language model (LLM)?

A large language model (LLM) is an AI trained on vast text to predict words and generate human-like language. See how LLMs work, their limits and examples.

What is agentic AI?

Agentic AI describes AI systems that plan, use tools and take real actions toward a goal, not just chat. See how the agent loop works, with examples.

What is retrieval-augmented generation (RAG)?

Retrieval-augmented generation (RAG) grounds AI answers in retrieved data to cut hallucination. Learn how RAG works, its components, and why it matters.

What is prompt engineering?

Prompt engineering is writing clear instructions that get reliable AI results. See techniques, examples, and why it matters less in 2026.

What is multimodal AI?

Multimodal AI understands more than text — it processes images, audio and documents together. A plain-English definition, examples and why it matters.

What is fine-tuning?

Fine-tuning adapts a pre-trained AI model on extra examples to change its behaviour. Learn what fine-tuning is and how it compares to RAG and prompting.

What is a context window?

A context window is the maximum amount of text (tokens) an AI model can read at once. Learn why size matters and what happens when it overflows.

What is an AI hallucination?

An AI hallucination is when an LLM states false information as fact. Learn why models hallucinate and how grounding and citations reduce it.

What are tokens in AI?

Tokens in AI are the chunks of text a model reads and writes. Learn how tokens work, why they set pricing and limits, and how MiyoMind meters usage.

What are embeddings?

Embeddings are lists of numbers that capture the meaning of text or images so AI can compare them. Learn what vector embeddings are and how they work.

What is a vector database?

A vector database stores data as numerical embeddings so AI can search by meaning, not keywords. Learn how it powers similarity search, RAG and AI memory.

What is function calling (tool use)?

Function calling, or tool use, lets an LLM decide when to call an external tool, pass it structured arguments, and use the result to answer. Plain guide.

What is a system prompt?

A system prompt is the hidden instruction that sets an AI's role, rules and persona before you chat. Learn what it is and how it shapes behaviour.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard that connects AI models to tools and data. Learn what MCP is, how it works, and why it matters.

What is conversational AI?

Conversational AI is technology that understands and replies in natural language. Learn how it works, how it differs from chatbots, and where it's used.

What is AI inference?

AI inference is running a trained model to produce outputs from new input. Learn how inference differs from training, why it costs money, and why it's metered.

What is a foundation model?

A foundation model is a large AI model trained broadly on vast data, then adapted to many tasks. Learn how foundation models work, with examples.