> 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/artificial-intelligence/ai-agents/ai-agents-run-automations/ai-agents-how-to-communicate-with-crm-via-broadcast.md).

# AI Agents - How to Communicate with CRM via Broadcast

## Configuring the Run Automations skill

To communicate with the CRM via the AI Agent, it is necessary to enable the skill and configure a new [**Agent Automation**](/en/topics/artificial-intelligence/ai-agents/ai-agents-run-automations.md).

Automations with **broadcast** are formed by a pair: one automation that sends and another that receives. It is a way of communication between two parts of the system that normally do not interact directly — such as the service context and the CRM, since the same lead can have multiple associated services and opportunities.\
\
For this automation to work correctly, some elements are essential:

* **Agent Condition**: Clearly define the criteria based on lead fields or message content. For example: when the lead says they are interested in a special promotion.
* **Agent Action**: The automation must include the action **"Send Broadcast"**. When this action is executed, a broadcast with the defined term will be sent through the lead.

Below is an example of how to send this signal to the CRM:

<figure><img src="/files/5a0ea0a8e6babd236bc130f356918ae768543f30" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/016c6066dc310e310e3bf233077de10b737b6593" alt=""><figcaption></figcaption></figure>

## Creating an automation in the CRM

A Funnel Automation will be created that will check all open opportunities. If a lead with an active opportunity in the CRM receives the broadcast, its stage will be updated automatically.

As a trigger, **"Broadcast received"**, will be used and as an action, **"Change the opportunity funnel/stage"**.

<figure><img src="/files/e0f6a20f76d72f6ab9fe26bb9cfb2b5293646c78" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/6cfceca90edf09e0d08f3dc15645ce199374d272" alt=""><figcaption></figcaption></figure>

## Testing automations

To verify if the automation is working correctly, you can check the history of the lead and the opportunity. You will be able to confirm whether the actions were executed as expected or if any error occurred during the process.

<figure><img src="/files/fca3da31872e47dc678c3619bf4b807ffc9fe9ec" alt=""><figcaption><p><em>Service within SAC 360.</em></p></figcaption></figure>

<figure><img src="/files/d1ffd30129b11d74c5b1510e87043e02078b93c2" alt=""><figcaption><p><em>Activity History, within Lead Full Data.</em></p></figcaption></figure>

<figure><img src="/files/8e4fc4dc7e3ebe816e33ded2fd0ae89559943261" alt=""><figcaption><p><em>Opportunity within the CRM.</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/artificial-intelligence/ai-agents/ai-agents-run-automations/ai-agents-how-to-communicate-with-crm-via-broadcast.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.