Glossary
AI terms, explained. No jargon.
A plain-language reference for every AI, automation, and software term we use across our writing and services.
A
- AI Agent
- A software system that uses a large language model to autonomously plan, reason, and execute multi-step tasks with minimal human supervision.Read: Agentic AI in Action →
- AEO (Answer Engine Optimization)
- The practice of structuring content so AI-powered search engines surface it as a direct answer rather than a blue link.Read: AEO for US Businesses →
- API (Application Programming Interface)
- A set of rules and protocols that allows different software applications to communicate with each other and exchange data.
- Automation
- Using technology to perform tasks with minimal human intervention, reducing manual effort and increasing consistency.Read: Business Process Automation in 2026 →
B
- Business Process Automation
- The use of software to automate repeatable, multi-step business workflows such as onboarding, invoicing, or lead routing.Read: BPA in 2026 →
C
- Copilot
- An AI assistant embedded within an existing tool that augments a user’s work rather than acting autonomously.Read: Copilot vs Custom AI →
- CRM (Customer Relationship Management)
- Software that tracks interactions with leads and customers, often enhanced with AI for scoring, routing, and follow-up.Read: AI Lead Qualification →
- Claude
- A large language model developed by Anthropic, known for safety-focused design and long-context reasoning capabilities.
D
- Data Pipeline
- A sequence of automated steps that moves, transforms, and loads data from one system to another for analysis or action.
E
- Embedding
- A numerical vector representation of text, images, or other data that captures semantic meaning, enabling similarity search and retrieval.Read: Understanding RAG →
- ETL (Extract, Transform, Load)
- A data integration pattern that extracts data from sources, transforms it into a usable format, and loads it into a destination system.
F
- Fine-tuning
- The process of training a pre-trained language model on a smaller, domain-specific dataset to improve its performance on specialised tasks.
G
- GPT (Generative Pre-trained Transformer)
- A family of large language models by OpenAI that generate human-like text by predicting the next token in a sequence.
- Guardrails
- Programmatic checks applied to AI inputs and outputs to enforce safety, accuracy, format, and policy compliance.Read: AI Automation Governance →
H
- Human-in-the-loop
- A design pattern where a human reviews, approves, or corrects AI-generated outputs before they are acted upon.Read: AI Agents vs Assistants →
- Hallucination
- When an AI model generates plausible-sounding but factually incorrect or fabricated information.
I
- Integration
- The process of connecting separate software systems so they share data and functionality, often via APIs or middleware.
K
- Knowledge Base
- A structured repository of documents, FAQs, and data that an AI system can query to provide accurate, grounded answers.Read: Understanding RAG →
L
- LangGraph
- A framework for building stateful, multi-step AI agent workflows as directed graphs with built-in persistence and human-in-the-loop support.
- LLM (Large Language Model)
- A neural network trained on vast text data that can understand, generate, and reason about natural language.Read: The Rise of AI →
- LoRA (Low-Rank Adaptation)
- An efficient fine-tuning technique that trains a small set of adapter weights rather than the full model, dramatically reducing compute cost.
M
- Multi-agent System
- An architecture where multiple AI agents collaborate, each handling a specialised sub-task, to solve complex problems.Read: Agentic AI in Action →
- MCP (Model Context Protocol)
- An open protocol that standardises how AI models connect to external data sources and tools, enabling plug-and-play integrations.
N
- n8n
- An open-source workflow automation tool that lets you connect apps and services via a visual node-based editor.Read: Zapier vs Custom Automation →
- Natural Language Processing (NLP)
- A branch of AI focused on enabling machines to understand, interpret, and generate human language.
O
- Orchestration
- The coordination of multiple AI models, tools, and services within a single workflow to complete a complex task.
- OpenAI
- An AI research company and the creator of GPT-4, ChatGPT, and the Assistants API, widely used for building AI-powered applications.
P
- Prompt Engineering
- The craft of designing inputs to a language model to elicit accurate, useful, and well-formatted responses.
- Pipeline
- A series of automated stages that data or code passes through, from ingestion to processing to delivery.
R
- RAG (Retrieval Augmented Generation)
- A technique that grounds LLM responses in real data by retrieving relevant documents from a knowledge base before generating an answer.Read: Deep Dive into RAG →
- Retrieval
- The process of searching and fetching relevant information from a data store, often using vector similarity or keyword matching.
S
- Serverless
- A cloud computing model where the provider manages infrastructure, automatically scaling compute resources per request with no idle cost.Read: Serverless-First Architecture →
- Schema
- A formal structure that defines the shape, types, and constraints of data, used in databases, APIs, and structured AI outputs.
- Structured Data
- Data organised in a predefined format (e.g., JSON-LD, tables) that machines can easily parse, index, and reason about.Read: SEO Survival Guide 2026 →
T
- Token
- The basic unit of text that a language model processes, typically a word, sub-word, or punctuation mark. Token counts determine cost and context limits.Read: The Cost Problem in Agentic AI →
- Tool-calling
- A capability that lets an LLM invoke external functions, APIs, or databases during a conversation to fetch live data or perform actions.
V
- Vector Database
- A database optimised for storing and querying high-dimensional vector embeddings, enabling fast semantic similarity search for RAG and recommendation systems.Read: Deep Dive into RAG →
W
- Workflow Automation
- The design and execution of automated sequences of tasks across tools and systems, triggered by events or schedules.Read: BPA in 2026 →
Z
- Zapier
- A popular no-code automation platform that connects thousands of apps through trigger-action workflows, often compared against custom-built solutions for scale.Read: Zapier vs Custom Automation →