> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/superagents/settings.md).

# Superagent settings

Configure a superagent's identity, behavior, models, channels and budget.

To open a superagent's settings, select **Settings** on its page, or from the menu on its card in **Your superagents**. Changes save automatically.

The settings page has six sections.

## Identity

| Setting     | Details                                                                    |
| ----------- | -------------------------------------------------------------------------- |
| **Name**    | Required, up to 128 characters                                             |
| **Purpose** | A short description of what the superagent is for. It's shown on its card. |
| **Colour**  | The colour of its orb in the app                                           |

## Objectives

The superagent's objectives, which you can edit, add to or remove. See [Objectives, KPIs and autonomy](/zerve-docs/superagents/objectives-kpis-and-autonomy.md).

## Persona and guardrails

| Setting        | What it does                               | Example                                                                                     |
| -------------- | ------------------------------------------ | ------------------------------------------------------------------------------------------- |
| **Persona**    | How the superagent should sound and behave | "Write like a senior quant: concise, numbers first, no hype."                               |
| **Guardrails** | Rules it must follow                       | "Never trade or recommend trading. Only use data we've licensed. Always state assumptions." |

The superagent follows its guardrails strictly. Neither the persona nor the guardrails can override Zerve's own safety rules.

## Model and effort

These settings choose which models the superagent and its team use. Each defaults to **Organization default**, which uses your organization's [model settings](/zerve-docs/administration/model-settings.md).

| Setting              | Used for                                                        |
| -------------------- | --------------------------------------------------------------- |
| **Superagent model** | The superagent itself, as it plans, coordinates and checks work |
| **Small effort**     | "Faster, cheaper model for lighter worker tasks."               |
| **Medium effort**    | "Default worker tier for typical delegated work."               |
| **Large effort**     | "Stronger model for hard worker tasks."                         |

When the superagent assigns work, it chooses small, medium or large for each task, so routine work can use a cheaper model and hard problems a stronger one.

{% hint style="info" %}
These effort settings choose **which model** a worker uses. They're separate from a model's **reasoning effort** (Low, Medium or High), which controls how much a model reasons before it answers. See [Models and effort](/zerve-docs/agents-in-the-workspace/models-and-effort.md).
{% endhint %}

## Channels

Connections that let people reach the superagent from outside Zerve, such as Slack. See [Channels](/zerve-docs/superagents/channels.md).

## Runtime and budget

### Autonomous mode

**Autonomous mode** is off by default. When it's on, the superagent keeps working through its backlog without being asked: when it finishes a turn with nothing in progress and open backlog items remaining, it starts the next one. It can also add worthwhile improvements to its own backlog and pursue them.

It stops when the backlog is empty, or when everything left is waiting on something, such as a decision from you.

Leave it off if you'd rather the superagent only works when you message it, a schedule fires or its team finishes something.

{% hint style="info" %}
Autonomous mode is different from an objective's [autonomy level](/zerve-docs/superagents/objectives-kpis-and-autonomy.md#autonomy). Autonomous mode controls whether the superagent keeps working on its own; autonomy levels control how freely it makes decisions while it works.
{% endhint %}

### Daily budget

**Daily budget (credits)** is the most the whole team can spend in a day. See [Budgets and credits](/zerve-docs/superagents/budgets-and-credits.md).

## Sharing a superagent

To share a superagent, select **Share** on its page. People you invite are notified.

People with view-only access can ask the superagent questions, but they can't start work, set schedules or change anything about it. See [Sharing and privacy](/zerve-docs/administration/sharing-and-privacy.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.zerve.ai/zerve-docs/superagents/settings.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.