AI jargon, in plain English.

Glossary terms

AI (artificial intelligence)

The umbrella term for software that does things we would normally expect to need human judgement: writing, reading, deciding, recognising. On its own it tells you almost nothing.

Do you need to care?Not about the umbrella word. When someone says a product "uses AI", ask what it actually does, exactly.

LLM (large language model)

The engine behind tools like ChatGPT, Claude and Gemini. Trained on huge amounts of text, it predicts what words come next, which makes it good at writing, summarising and answering.

Do you need to care?Yes. When people say "AI" today they usually mean an LLM. You need to know what it is good at, not how it works.

Prompt

The instruction you give an AI. Better instructions, more context and a clear example of the tone you want get better results.

Do you need to care?Yes, but do not overthink it. It is mostly just being specific, the same skill as briefing a new employee well.

Hallucination

When an AI confidently makes something up: a fake statistic, an invented policy, a plausible wrong answer. It has no idea it is wrong.

Do you need to care?Absolutely. The rule it forces: AI drafts, you check. Never let an unreviewed answer reach a customer, contract or tax return.

Automation

Software doing a task without you: a missed call triggers a text-back, an overdue invoice triggers a reminder. Often just simple rules, and plenty of it involves no AI at all.

Do you need to care?More than any other word here. Boring, rule-based automation often pays for itself faster than anything with "AI" in the name.

No-code

Tools you assemble by clicking and connecting rather than programming. Zapier and Make are the big names: the glue between the apps you already use.

Do you need to care?Yes. No-code is how non-technical owners build real automations, and it is most of what we use in the workshop.

Agent

An AI that does not just answer but takes a series of actions to finish a job: reading emails, deciding which need replies, drafting them, filing the rest.

Do you need to care?Increasingly, but be sceptical of the label. Ask what the "agent" actually does, step by step. If the seller cannot say, walk away.

Chatbot

A program that holds a conversation, usually on a website or WhatsApp. Modern, AI-powered ones can genuinely answer questions about your prices, availability and services.

Do you need to care?If you get repetitive enquiries, yes. Give it your real information and give people an obvious route to a human.

API

The plug socket that lets one piece of software talk to another. When your booking system texts a customer, an API is doing it.

Do you need to care?Only enough to not be intimidated. The sentence to remember: API means it connects.

Token

The chunks of text an AI reads and writes, roughly three-quarters of a word each. Many tools are priced by the token, so bills scale with use.

Do you need to care?Only when comparing prices. Otherwise ignore it.

RAG (retrieval-augmented generation)

A setup where the AI looks things up in your documents (your price list, policies, past quotes) before answering, instead of relying on general training.

Do you need to care?Know the idea, skip the acronym. "We use RAG" just means "it reads your documents first". That is a good thing.

Context window

How much an AI can read and hold in mind at once, measured in tokens. A bigger window means it can take in a longer document or conversation before it starts forgetting the start.

Do you need to care?A little. It is why very long chats drift, and why "give it a brain" matters: you feed it the right context, not everything.

No terms match that. Try a shorter word.