AI Glossary
Short, clear definitions of terms that come up often in enterprise AI. For each term we explain how it works, where it is used and what to watch for.
Terms
AI Agent
An AI agent is an AI structure that not only answers questions but plans steps towards a goal and can perform actions with defined tools (APIs, databases, company systems).
Hallucination
A hallucination is when an AI model produces information that looks fluent and convincing but is wrong or has no source.
Large Language Model (LLM)
A large language model (LLM) is an AI model trained on very large amounts of text that can understand and generate text.
On-Premise LLM
An on-premise LLM means running a large language model on an organisation's own servers or infrastructure it controls, rather than with a cloud provider.
Open-Weight Model
An open-weight model is an AI model whose trained parameters (weights) are published so they can be downloaded and used.
Prompt Engineering
Prompt engineering is the design and testing of instructions, context, examples and output format to get reliable, consistent output from an AI model.
RAG (Retrieval-Augmented Generation)
RAG (Retrieval-Augmented Generation) means an AI model first retrieves relevant passages from an organisation's own documents and grounds its answer in them.
Let's work together
Let us listen to your processes and goals, and evaluate together where AI can add value.
Send an email