Enterprise AI, plain English

The AI Glossary

28 terms every decision-maker, architect, and product lead should know before scoping an AI project.

Agentic Workflow

Applications

A structured pipeline where an LLM makes decisions at defined branch points, but the overall flow is deterministic.

Read definition

AI Agent

Applications

An LLM-driven system that plans, calls tools, and executes multi-step tasks autonomously.

Read definition

AI Governance

Governance

The framework of policies, controls, and audits that govern how AI is built and used in an organization.

Read definition

Chain-of-Thought (CoT)

Techniques

Prompting technique where the model is asked to reason step-by-step before answering.

Read definition

Computer Vision

Applications

The field of AI that enables machines to interpret and act on visual information from images and video.

Read definition

Context Window

Foundations

The maximum number of tokens a model can process in a single request (input + output).

Read definition

Edge AI

Infrastructure

Running AI models on-device or on local hardware instead of in the cloud.

Read definition

Embedding

Foundations

A numerical vector that captures the semantic meaning of a piece of content.

Read definition

Embedding Model

Models

A neural network that converts text (or images, audio) into dense numeric vectors capturing meaning.

Read definition

Fine-Tuning

Techniques

Continuing training of a pre-trained model on domain-specific data to specialize its behavior.

Read definition

Function Calling / Tool Use

Techniques

Structured way for an LLM to invoke external functions or APIs with typed arguments.

Read definition

Guardrails

Governance

Structured constraints that keep LLM outputs safe, on-scope and correctly formatted.

Read definition

Hallucination

Foundations

When an LLM generates plausible-sounding but factually incorrect output.

Read definition

Hybrid Search

Techniques

Combining dense (semantic) retrieval with sparse (keyword / BM25) retrieval for better recall.

Read definition

Large Language Model (LLM)

Models

A neural network trained on massive text corpora to understand and generate human-like language.

Read definition

LoRA (Low-Rank Adaptation)

Techniques

A parameter-efficient fine-tuning technique that trains small adapter matrices instead of full model weights.

Read definition

MCP (Model Context Protocol)

Infrastructure

An open standard that lets LLMs discover and call external tools, data, and services in a uniform way.

Read definition

MLOps

Infrastructure

DevOps practices adapted to the lifecycle of machine learning and AI systems.

Read definition

Multimodal AI

Models

Models that understand and generate across multiple input types — text, images, audio, and video.

Read definition

OCR (Optical Character Recognition)

Applications

Extracting machine-readable text and structure from images, scans, and PDFs.

Read definition

Prompt Engineering

Techniques

The practice of designing model inputs to produce reliable, task-specific outputs.

Read definition

Prompt Injection

Governance

An attack where malicious instructions hidden in inputs override or subvert the LLM's intended behaviour.

Read definition

Quantization

Infrastructure

Compressing a model by reducing the numerical precision of its weights, cutting memory and speed cost.

Read definition

Reranker

Techniques

A second-stage model that re-scores retrieved candidates to improve final ranking quality in RAG.

Read definition

Retrieval-Augmented Generation (RAG)

Techniques

A pattern that grounds LLM answers in your private documents by retrieving relevant snippets at query time.

Read definition

RLHF (Reinforcement Learning from Human Feedback)

Techniques

Training technique that aligns LLMs to human preferences using reinforcement learning on preference data.

Read definition

Small Language Model (SLM)

Models

A compact LLM (1B–15B parameters) tuned for cost, latency, and on-device deployment.

Read definition

Vector Database

Infrastructure

A database optimized for storing and searching high-dimensional embeddings by similarity.

Read definition

Ready to move from vocabulary to velocity?

Take our 3-minute AI Readiness assessment and get a tailored roadmap for your organization.