Skip to main content

Labs Tool

Enterprise AI Glossary

Plain-English definitions of enterprise AI terminology.

A

Agent

An AI system that can perceive its environment, make decisions, and take actions to achieve goals. Enterprise agents can call tools, retrieve information, and execute multi-step workflows.

AI Concepts

Agentic Workflow

A workflow where AI agents autonomously plan, execute, and iterate on multi-step tasks, potentially calling external tools and APIs.

AI Concepts

C

Chunking

The process of splitting large documents into smaller segments before embedding them into a vector database. Chunk size affects retrieval quality and context window usage.

RAG

Context Window

The maximum amount of text an LLM can process in a single request. Larger context windows allow more retrieved documents to be included in the prompt.

LLM

E

Embedding

A numerical vector representation of text that captures semantic meaning. Similar texts have embeddings that are close together in vector space.

RAG

F

Fine-tuning

The process of further training a pre-trained model on domain-specific data to improve performance on specific tasks.

AI Concepts

G

Grounding

The practice of connecting AI responses to verified, factual sources — typically your enterprise knowledge base — to reduce hallucinations.

RAG

H

Hallucination

When an LLM generates plausible-sounding but factually incorrect information. RAG and grounding techniques are used to reduce hallucinations in enterprise deployments.

AI Concepts

Hybrid Search

A retrieval approach that combines dense vector search (semantic) with sparse keyword search (BM25) to improve recall and precision.

Search

K

Knowledge Graph

A structured representation of entities and their relationships, used to enhance AI retrieval with contextual connections between concepts.

Knowledge

L

LangChain

An open-source framework for building LLM-powered applications, providing abstractions for chains, agents, memory, and tool use.

Frameworks

LangGraph

A library for building stateful, multi-actor AI applications using graph-based workflows. Used for complex agent orchestration.

Frameworks

LLM

Large Language Model. A neural network trained on vast amounts of text data, capable of generating, summarising, translating, and reasoning about text.

LLM

M

Multi-model Routing

The practice of directing different types of queries to different AI models based on cost, capability, latency, or compliance requirements.

Architecture

P

pgvector

A PostgreSQL extension that adds vector similarity search capabilities, enabling hybrid relational + vector storage in a single database.

Infrastructure

Prompt Engineering

The practice of designing and optimising input prompts to elicit better, more accurate, or more useful responses from LLMs.

AI Concepts

R

RAG

Retrieval-Augmented Generation. A technique that enhances LLM responses by first retrieving relevant documents from a knowledge base and including them in the prompt context.

RAG

RBAC

Role-Based Access Control. A security model where access to resources is determined by a user's role within an organisation.

Security

Re-ranking

A post-retrieval step that re-orders search results using a more powerful model to improve relevance before passing them to the LLM.

Search

S

Semantic Search

Search that understands the meaning and intent behind a query, rather than just matching keywords. Powered by vector embeddings.

Search

SSO

Single Sign-On. An authentication scheme that allows users to log in once and access multiple systems. Essential for enterprise AI deployments.

Security

System Prompt

Instructions given to an LLM at the start of a conversation that define its persona, constraints, and behaviour. Critical for enterprise AI assistants.

LLM

T

Token

The basic unit of text processed by an LLM. Roughly 4 characters or 0.75 words. LLM pricing and context limits are measured in tokens.

LLM

V

Vector Database

A database optimised for storing and querying high-dimensional vector embeddings. Examples include Pinecone, Weaviate, Qdrant, and pgvector.

Infrastructure

Z

Zero-shot

The ability of an LLM to perform a task without any task-specific examples in the prompt. Contrast with few-shot prompting.

AI Concepts