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

# Variants

> Dimensions the output varies across — language, brand, audience — and how to tell a dimension from a field.

A **variant** is one dimension of customisation. Language, brand, audience, and persona are the usual ones.

Each dimension has **options**, and each option carries **fields** describing it:

```json theme={null}
{
  "label": "Audience",
  "instruction": "Adapt tone, complexity, and messaging to resonate with this target group.",
  "options": {
    "B2B": [
      { "key": "Description", "value": "Business professionals and decision-makers" },
      { "key": "Communication style", "value": "Professional, outcome-focused" }
    ],
    "B2C": [
      { "key": "Description", "value": "General public" },
      { "key": "Communication style", "value": "Friendly and conversational" }
    ]
  }
}
```

| Part          | Meaning                                                                              |
| ------------- | ------------------------------------------------------------------------------------ |
| `label`       | The dimension name. Sessions bind to it, and rules can be scoped by it.              |
| `instruction` | Prose telling the model how to use this dimension. Sensible defaults exist per type. |
| `options`     | Option name to a list of `key`/`value` fields.                                       |

## One option per dimension, per session

When a session starts, exactly one option is chosen per dimension — and **each combination produces its own separate output**.

Two languages and two audiences is four generations per record, and four times the cost.

## Dimension or field?

<Info>
  **The deciding test:** does this thing need its own output candidate per option?

  If yes, it is a dimension. If it is additional information that shapes the *same* output — tone notes, reading level, terminology — it is a field on an existing option.
</Info>

Getting this wrong in the direction of too many dimensions is expensive, because the combinations multiply. Keep to three or four dimensions at most.

## Why variants, and not the prompt

Variant fields are injected into the generation prompt **and** into every AI quality check's context. That is what makes them different from special instructions or prompt text.

Anything that must be *quality-checkable* — brand voice, terminology, audience traits — belongs in a variant, because it is the only way the checker knows what the writer was told.

## Curating fields

* Two or three fields per option is the safe baseline
* Four to six needs testing
* Seven or more risks the model quietly dropping some

<Tip>
  Every field is a constraint the model has to hold simultaneously. If removing a field would not change the output, remove it.
</Tip>

Keep the default instruction unless you have a specific reason to change it.

## Scoping rules to variants

A quality rule can be scoped to specific options — a forbidden-terms list that applies only to Danish, a formality check only for German. A rule that does not match the session's combination is not even shown to the generator. [Quality checks](/speedtrain/key-concepts/quality-checks)