# Traits

> Switches that change how the agent's loop behaves — whether its character reaches the model, and whether it tidies its own memory on a schedule.

A **trait** turns one behavior of the agent on or off. Unlike the [system prompt](/docs/build/system-prompt/), which is text you write, a trait is a switch: the setting stays where it already lives, and the trait decides whether it is used.

## The traits

| Trait | What turning it on does |
| --- | --- |
| **Personality** | The character you set in the agent's [profile](/docs/build/identity/) is included in what the model reads. With it off, the agent works from its prompt alone. |
| **Self-evolving** | The agent reviews and tidies its own [memory](/docs/capabilities/memory/) on a schedule, as a [routine](/docs/automate/routines/) you can see and edit like any other. |

<Screenshot
  name="studio-trait"
  alt="The trait section: Personality and Self-evolving, each a single switch with a sentence explaining what turning it on does."
/>

## When to use them

**Personality** is worth turning on when tone matters — an agent that talks to customers, or one whose replies you read all day. Leave it off when you want the agent to be plain and predictable, or when you are [tuning a prompt](/docs/build/iterating/) and want one fewer variable.

**Self-evolving** earns its place on an agent that has been running for weeks and has accumulated memories it no longer needs. On a new agent there is nothing to tidy.

<Aside type="note" title="Turning a trait off keeps its settings">
  Off is not erased. The character stays on the profile and the routine stays in
  the routine list — the trait only stops using them. Turning it back on restores
  the previous behavior.
</Aside>

## Limits

- Traits are per agent.
- The personality trait does not create a personality; it carries the one already on the profile. Change the character in [Identity](/docs/build/identity/).
- Self-evolving works through a normal routine, so it is subject to the same rules — including that an unattended run cannot ask you anything.
- Changes apply to the agent's next [run](/docs/work/runs/).

## Related

<CardGrid>
  <LinkCard
    title="Identity and profile"
    href="/docs/build/identity/"
    description="Where the character the personality trait carries is set."
  />
  <LinkCard
    title="Memory"
    href="/docs/capabilities/memory/"
    description="What the self-evolving trait tidies."
  />
  <LinkCard
    title="The context window"
    href="/docs/work/context-window/"
    description="Traits are part of what the model reads on every step."
  />
</CardGrid>