> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/19.latest/using-the-api/chat/system-prompts.md).

# System Prompts

Control AI behavior with system prompts in chat requests.

System prompts set the AI model's role, personality, and constraints. They are sent as the first message in a conversation and shape how the model responds to all subsequent messages.

## Adding a System Prompt

Include a `ChatRole.System` message at the start of your messages list:

{% code title="SystemPrompt.cs" %}

```csharp
var messages = new List<ChatMessage>
{
    new(ChatRole.System, "You are a helpful content editor for an Umbraco website. " +
                         "Always respond in a professional tone. " +
                         "Keep answers concise and actionable."),
    new(ChatRole.User, "Suggest a better title for my blog post about CMS platforms.")
};

var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("content-editor"),
    messages);
```

{% endcode %}

## Profile-Level System Prompts

Rather than including system prompts in every request, configure them on the profile. The system prompt is then applied automatically:

{% code title="ProfileSystemPrompt.cs" %}

```csharp
var profile = new AIProfile
{
    Alias = "content-assistant",
    Name = "Content Assistant",
    Capability = AICapability.Chat,
    ConnectionId = connectionId,
    Model = new AIModelRef("openai", "gpt-4o"),
    Settings = new AIChatProfileSettings
    {
        SystemPromptTemplate = "You are a content assistant for an Umbraco website. " +
                               "Help editors write engaging content."
    }
};

await _profileService.SaveProfileAsync(profile);
```

{% endcode %}

When using this profile, the system prompt is injected automatically. You only need to send user messages:

{% code title="UsingProfilePrompt.cs" %}

```csharp
var messages = new List<ChatMessage>
{
    new(ChatRole.User, "Write a meta description for our About page.")
};

// The profile's system prompt is prepended automatically
var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("content-assistant").WithProfile(profileId),
    messages);
```

{% endcode %}

{% hint style="info" %}
If you include a system message in your request and the profile also has a system prompt, both are sent. The profile's system prompt comes first.
{% endhint %}

## System Prompt Best Practices

1. **Be specific about the role** - "You are a content editor" is better than "You are helpful"
2. **Set constraints early** - Include tone, length, and format requirements
3. **Use profiles for reuse** - Configure system prompts on profiles rather than hardcoding them in every request

## Related

* [Basic Chat](/ai-in-umbraco/19.latest/using-the-api/chat/basic-chat.md) - Sending chat requests
* [Profiles](/ai-in-umbraco/19.latest/concepts/profiles.md) - Configuring profile settings


---

# 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.umbraco.com/ai-in-umbraco/19.latest/using-the-api/chat/system-prompts.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.