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

# Designing Strong Prompt Suites

<Note>
  A strong prompt suite tests one behavior family from multiple angles.
</Note>

***

## The rule

One suite should have one primary purpose.

Good suite purpose:

```text theme={"dark"}
Test whether Lucia routes disorientation language into emotional-operational containment.
```

Bad suite purpose:

```text theme={"dark"}
Test Lucia.
```

***

## The 1–10 prompt range

The custom launcher allows up to 10 prompts.

Use the limit deliberately.

Recommended sizes:

| Purpose                        | Prompt Count |
| ------------------------------ | -----------: |
| Quick smoke                    |            1 |
| Narrow bug check               |          3–5 |
| Behavior family refinement     |          5–8 |
| Pre/post regression comparison |         8–10 |

***

## Prompt variation types

A strong suite uses variants:

### Direct phrase

```text theme={"dark"}
I'm overwhelmed.
```

### Near-neighbor phrase

```text theme={"dark"}
I'm frazzled.
```

### Indirect emotional signal

```text theme={"dark"}
I have no idea what to do.
```

### Trust-state signal

```text theme={"dark"}
I don't trust that I know what's going on.
```

### Operational hybrid

```text theme={"dark"}
Kids just got home and I'm overwhelmed.
```

***

## What to avoid

Avoid prompts that are too broad to interpret:

```text theme={"dark"}
Help.
```

Avoid mixing unrelated behaviors unless the suite is explicitly a mixed-mode test.

Avoid changing prompt text between before/after runs unless you are intentionally creating a new suite version.

***

## Suite notes

When creating a suite, write down:

* purpose
* expected mode
* known failure pattern
* desired behavior
* version number

Use [Custom Suite Template](/eval-labs/templates/custom-suite-template).