RESOURCES
Glossary
Plain-language definitions for common AI terms.
LLM (Large Language Model)
A type of AI system trained on large amounts of text that can understand and generate human-like language. This is the technology behind tools like ChatGPT.
RAG (Retrieval-Augmented Generation)
A method where an AI system looks up relevant information from your own documents before answering, so its responses are grounded in your actual content rather than general knowledge.
Inference
The process of an AI model actually generating a response to a question — essentially, the AI "thinking" and producing an answer.
Vector Database
A specialized way of storing documents that allows an AI system to quickly find the most relevant information based on meaning, not just exact keyword matches.
Knowledge Base
An organized collection of your company's documents and information, structured so it can be searched quickly and accurately — by people or by an AI assistant.
Prompt Engineering
The practice of carefully wording questions or instructions to an AI system to get more accurate, useful responses.
On-Premises / Local Deployment
Running software (including AI) on your own hardware and network, rather than on a third-party company's servers over the internet.
Cloud AI
AI services accessed over the internet and hosted on a third-party provider's servers (such as OpenAI, Anthropic, or Google), rather than on your own infrastructure.