Plain-language definitions of the AI terms operators actually run into.
Terms
- LLM
- Large Language Model — the AI that generates and understands text.
- AI agent
- An AI system that can take multi-step actions toward a goal, not just answer.
- Prompt
- The instruction you give an AI.
- RAG
- Retrieval-Augmented Generation — feeding an AI your own data so answers are grounded.
- Context window
- How much text an AI can consider at once.
- Fine tuning
- Further-training a model on specific data for a specific job.
- Embeddings
- Numeric representations of meaning used for search and matching.
- Vector database
- A store for embeddings that powers semantic search.
- MCP
- Model Context Protocol — a standard for connecting AI to tools and data.
- Workflow automation
- Chaining steps so a process runs with little human input.
- Inference
- The model generating an output from an input.
- Token
- A chunk of text the model reads/writes; usage is measured in tokens.
Ready to build?
Learn the fundamentals, then run them inside the network.
Join the network
