# Additional settings

This step allows you to define how the output of your Agent Crew will be used once a task is complete. You can either send the results to external systems or forward the output to other agents for further processing.

#### **Configure agent output** <a href="#configure-agent-output" id="configure-agent-output"></a>

This section is used to define external destinations where the agent’s output will be sent.

* Click ‘+ Add an output’ to open a side panel titled ‘Add Output Source’.

<figure><img src="/files/E7tfwI9EXErLNaRJv73r" alt=""><figcaption></figcaption></figure>

* The panel displays a list of supported output integrations, including:
  * **Google Docs**
  * **Google Sheets**
  * **Gmail**
  * **SendGrid**
  * **Notion**
  * **Webhook (Send processed data from ZBrain)**
* Once selected, the destination will be listed under this section with a connection status indicator (green dot for active).
* To remove an output, click the trash icon next to it.

#### **Notify agents** <a href="#notify-agents" id="notify-agents"></a>

Use this section to forward the output of the crew to another agent.

* Click the ‘Add’ button to open a side panel titled ‘Select Agent’.

<figure><img src="/files/Q6d01PtYXXgj3MQRrhuO" alt=""><figcaption></figcaption></figure>

* Use the search bar to find agents you’ve created previously. The panel lists available agents along with their names and the last updated timestamp.

This enables the creation of multi-step flows where the result from one agent becomes the input for the next.

After configuring output destinations, click ‘Deploy Agent’ to deploy the crew.


---

# 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.zbrain.ai/zbrain-documentation/zbrain-builder/zbrain-ai-agents/agent-crew/additional-settings.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.