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

# Agent behaviour — tone, system prompt, and fallback settings

> Configure your Agenvik agent's system prompt, tone (friendly, professional, neutral), verbosity, fallback message, and guardrails to control how it responds.

**Behaviour** controls how an Agent responds when it uses your Knowledge Sources.

## What you will learn

* What each Behaviour field does
* How to write useful instructions
* How to create safer fallback and guardrail behavior

## Open Behaviour

Open an Agent and scroll to the **Behaviour** card.

<Frame>
  <img src="https://mintcdn.com/arokart/bVqC9z00iBm9fRgB/images/product-ss/behaviour-settings.png?fit=max&auto=format&n=bVqC9z00iBm9fRgB&q=85&s=f13da6260b048a89f14e0e14d0354e8d" alt="Behaviour settings placeholder" width="1512" height="943" data-path="images/product-ss/behaviour-settings.png" />
</Frame>

## System Prompt

Use the **System Prompt** to describe the Agent's role and goal. Keep it specific.

Good prompts usually include:

* The business or team the Agent represents
* The topics it should help with
* The kind of answer it should give
* When it should ask a follow-up question
* When it should direct the visitor to support

## Tone

Choose the tone that matches the audience:

* **Friendly** for approachable customer support
* **Professional** for sales, business, or account workflows
* **Neutral** for factual help center experiences

## Verbosity

Choose the response length:

* **Short** for quick FAQ answers
* **Balanced** for most support experiences
* **Detailed** for setup, troubleshooting, or technical explanations

## Fallback Message

The **Fallback Message** is shown when the Agent cannot answer confidently. Use a helpful message that sets expectations and offers a next step.

Example:

```text theme={null}
I do not have enough information to answer that yet. Please contact our support team and include what you were trying to do.
```

## Guardrails

Use **Guardrails** to define boundaries. For example, tell the Agent not to make pricing promises, not to answer outside your product scope, or to ask for a human handoff when sensitive information is involved.

## Save and test

Click **Save**, then test the Agent in the **Web Preview** with real customer-style questions.

<Frame>
  <img src="https://mintcdn.com/arokart/bVqC9z00iBm9fRgB/images/product-ss/agent-preview.png?fit=max&auto=format&n=bVqC9z00iBm9fRgB&q=85&s=e8cd2f0842d1031234a3b3a7e3136655" alt="Agent preview placeholder" width="1512" height="943" data-path="images/product-ss/agent-preview.png" />
</Frame>

## Next steps

<CardGroup cols={2}>
  <Card title="Web Channel" icon="message-square" href="/user-guides/agents/web-channel">
    Configure the visible web chat experience.
  </Card>

  <Card title="Best practices" icon="sparkles" href="/user-guides/quick-start/best-practices">
    Learn how to refine instructions and source content.
  </Card>
</CardGroup>
