> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aperium.apps.hillspire.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI vocabulary & mental models

> The shared language: model, prompt, token, context window, hallucination, agent, and tool.

You are about to hear these words in meetings, in email, and inside Aperium itself. This page is the shared dictionary so nobody has to nod along. Nothing here is technical — by the end you will be able to use all seven words correctly and hold the right mental picture of what the thing actually is.

## The one mental model

If you remember only one idea, make it this one: an AI language model is a **very good next-word predictor** trained on an enormous amount of text. Think of it as autocomplete that has read the internet. You give it words; it predicts what plausibly comes next, piece by piece, until it has an answer.

<Warning>
  A model produces **plausible** text — usually right, but never guaranteed. It is **not** a search engine, **not** a database, and **not** a person. That single distinction explains most of the surprises people have.
</Warning>

## The seven words

<AccordionGroup>
  <Accordion title="Model — the brain">
    The trained system that turns your input into a response. Claude and GPT are models. Different models differ in capability, speed, and cost. Aperium runs on Claude models. When someone says "the model," they mean the brain — not the app, and not your prompt.
  </Accordion>

  <Accordion title="Prompt — what you ask">
    Whatever you type or ask. The quality of the prompt is the biggest lever on the quality of the answer: the same task, phrased vaguely versus specifically, produces very different results. There is a whole page on doing this well — see [Prompting & getting good results](/literacy/prompting).
  </Accordion>

  <Accordion title="Token — a chunk of text">
    The unit of text the model reads and writes — roughly three-quarters of a word. You will mostly hear "tokens" when people talk about length or cost.
  </Accordion>

  <Accordion title="Context window — what it can hold in mind at once">
    How much the model can consider at one time: your prompt, any files you attach, and its own reply. Picture a desk of limited size — pile too much on and older things fall off the edge. That is why a very long document or a very long chat can start to "forget" how it began.
  </Accordion>

  <Accordion title="Hallucination — confident but false">
    When the model states something false in a confident voice — a made-up number, a citation that does not exist. It happens because the model predicts plausible text and has no built-in sense of true versus false. It is not lying; lying needs intent, and it has no notion of truth, only plausibility.
  </Accordion>

  <Accordion title="Agent — talk plus do">
    A plain chatbot only talks. An agent can take actions: search a system, read a file, send a message, query data. Giving an agent actions that reach *our* systems is exactly what makes Aperium more than a generic chatbot.
  </Accordion>

  <Accordion title="Tool — one action an agent can take">
    A specific capability an agent uses to act, such as searching Salesforce or looking up a contract. Chatbot equals talk; agent equals talk plus tools. See [How agents, tools & skills work](/literacy/agents-tools-skills).
  </Accordion>
</AccordionGroup>

## The habit to carry forward

<Tip>
  Confident does not mean correct. A model always sounds sure of itself, whether it is right or wrong — so a confident tone is not evidence of accuracy. This is the reason verification matters, and why later modules spend time on it.
</Tip>

## Where to go next

<Card title="How LLMs actually work" icon="brain" href="/literacy/how-llms-work">
  Go one level deeper on the mental model: how the model learned, what it is doing word by word when it answers, and why the same mechanism makes it both fluent and confidently wrong.
</Card>