> For the complete documentation index, see [llms.txt](https://docs.sprinthub.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sprinthub.com/en/topics/relate/automation-flows/common-questions/automation-flow-ai-powered-personalized-message-sending.md).

# Automation Flow - AI-Powered Personalized Message Sending

Bulk sends with AI: personalize using the Copilot token and lead fields.

## Configuring the Trigger Flow

In this example, we will use a segment containing all contacts who filled out Sprinthub University's pre-enrollment form, providing their name, email, and course of interest.\
This data — especially the **name** and the **course of interest** — will be used later to generate a personalized message.

{% hint style="info" %}
To learn about the different ways to trigger an Automation Flow, [click here](/en/topics/relate/automation-flows/tutorial-videos/automation-flow-ways-to-trigger.md).
{% endhint %}

<figure><img src="https://684109703-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9FzUKkagBNy5uQ7AtGNa%2Fuploads%2FS5mHweplazhK7KFTsloC%2Fimage.png?alt=media&amp;token=9bc3d5c0-c8ec-4ca5-893e-1aebcdf44b59" alt=""><figcaption><p><em>Automation Flow editing screen.</em></p></figcaption></figure>

<figure><img src="https://684109703-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9FzUKkagBNy5uQ7AtGNa%2Fuploads%2FAopiFIamk6ddo4oH7OwL%2Fimage.png?alt=media&amp;token=b7e2b2e1-36f6-405b-ba45-a0bdd7a92805" alt=""><figcaption><p><em>Send WhatsApp action.</em></p></figcaption></figure>

## Configuring Send WhatsApp Action

By using the token `{copilot=...}`, we can insert line breaks within the content to make the prompt more organized and readable. It is worth noting that the token can be used anywhere in the "Send Message" block, according to your preference.

In addition, it is possible to define the **level of creativity of the AI's response** directly in the token, using the prefixes:

* `temp__creative` – for more creative responses with greater variation (more "random").
* `temp__deterministic` – for more direct and predictable responses (more "objective").

Token used in the message:

```
{copilot=temp__creative
Create a short and engaging message using the lead's course of interest, which would be '{contactfield=curso_interesse}', from Sprinthub University. The lead's name is '{contactfield=firstname}'
The message should remind them that registrations for this course are open until October 20 and encourage the lead not to miss the deadline. Use a few emojis.
}
```

<figure><img src="https://684109703-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9FzUKkagBNy5uQ7AtGNa%2Fuploads%2FHeU6MDr6cKwu7q9l5a9M%2Fimage.png?alt=media&amp;token=4894e0a7-4bde-4c65-a7ef-86ea442ff185" alt=""><figcaption><p><em>Writing a prompt inside the Copilot token.</em></p></figcaption></figure>

{% hint style="warning" %}
Mass sends with AI can generate high credit usage on the platform used (e.g., OpenAI or Gemini). Therefore, it is recommended to prioritize personalized messages for leads with greater conversion potential.
{% endhint %}

## Checking Trigger Messages

As shown in the example below, the contact Neto received a personalized message about the registration deadline, based on the course-of-interest field, which would be Veterinary Medicine.

<figure><img src="https://684109703-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9FzUKkagBNy5uQ7AtGNa%2Fuploads%2FfhK5WowDeumnJ6WELE9d%2Fimage.png?alt=media&amp;token=b9b0e3d7-11f5-4700-a728-2e32d19172cc" alt=""><figcaption><p><em>Support with the trigger.</em></p></figcaption></figure>


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.sprinthub.com/en/topics/relate/automation-flows/common-questions/automation-flow-ai-powered-personalized-message-sending.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.