# Automation Flow - Triggering Personalized Messages with AI

## Setting Trigger Flow

In this example, we will use a segment containing all contacts who filled out the Sprinthub University pre-enrollment form, providing name, email and course of interest.\
These 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="/files/fbaaa5e028f0fae9da40502cea84a90acacb2220" alt=""><figcaption><p><em>Automation Flow editing screen.</em></p></figcaption></figure>

<figure><img src="/files/f13ae7226184ed6624ff55ea87206524b7ec28d9" alt=""><figcaption><p><em>Send Whatsapp action.</em></p></figcaption></figure>

## Configuring Send Whatsapp Action

When we use 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 in any part of the "Send Message" block, according to your preference.

In addition, it is possible to set the **level of creativity of the AI 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, 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 that registrations for this course are open until October 20th and encourage the lead not to miss the deadline. Use some emojis.
}
```

<figure><img src="/files/85555ee9ac969080c87dcbefa4116d5706286ec0" 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 consumption on the platform used (e.g.: OpenAI or Gemini). Therefore, it is recommended to prioritize personalized messages for leads with higher conversion potential.
{% endhint %}

## Checking Trigger Messages

As the example below shows, 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="/files/a4486ab324ee283bccd6f2601c0c2148bc12492c" alt=""><figcaption><p><em>Support with the send.</em></p></figcaption></figure>


---

# Agent Instructions: 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:

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

The question should be specific, self-contained, and written in natural language.
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.