> For the complete documentation index, see [llms.txt](https://docs.ebbot.ai/ebbot-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ebbot.ai/ebbot-docs/core-capabilities/automations/quickstart-email-agent.md).

# Quickstart - Email Agent

Going from a manual process to a live automation takes only a few minutes. This guide will walk you through the essential steps to get your first workflow and your Email agent up and running.

## Get started with Email agent in Automations

Follow these steps to get your Email agent up and running.

**1. Access the Platform**

Log in to your Ebbot account and head to the **Automations** section. This is your mission control, where you'll find your [Workflows dashboard](https://automations.ebbot.eu/flows), active integrations, and performance metrics.

**2. Connect your first Integration**

Before you can build a workflow, you need to give Ebbot permission to talk to your other tools.

1. Navigate to the **Integrations** tab.
2. Browse the library for the tools you use (like TOPdesk, Slack, or Zendesk).
3. Click **Install** and follow the prompts to authenticate.
4. Once connected, Ebbot will automatically unlock a set of custom **Triggers** and **Actions** specific to that tool.

**3. Launch the Flow Builder**

With your integrations ready, you have two paths to start building:

**Option A: Start from scratch**

If you have a specific custom logic in mind, you can create a new workflow from scratch on the [Workflows page](https://automations.ebbot.eu/flows). This opens a blank canvas in the **Flow Builder**, giving you total control over the automation's structure.

**Option B: Use a Template**

If you want to move fast, head to the **Templates** tab on the [Workflows page](https://automations.ebbot.eu/flows) after installing an integration. Here you'll find pre-configured workflows for common scenarios (like auto-replying to tickets). You can select which workflows you would like to activate and fill the required fields. The template will then become an unpublished workflow which you can edit in the Flow Builder to match your needs. *For more information about using templates, see* [*Templates*](/ebbot-docs/core-capabilities/automations/templates.md)*.*

**4. Validate and go live**

Before you hit publish, the Flow Builder acts as a safety net. It will highlight any nodes that are missing required configuration or aren't properly connected.

1. Ensure all red error indicators are resolved.
2. Double-check your logic and LLM prompts.
3. Click **Publish** to activate the workflow.

*Pro-tip: We always recommend testing new workflows against a staging or sandbox environment before connecting them to your live production data.*

**5. Monitor and iterate**

Once your workflow has 'left the nest,' you can track its performance in real-time. Use the [Dashboard & Monitoring](https://docs.ebbot.ai/ebbot-docs/automations/dashboard-and-monitoring) page to see successful runs, inspect logs for failures, and fine-tune your logic as your needs evolve.


---

# 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.ebbot.ai/ebbot-docs/core-capabilities/automations/quickstart-email-agent.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.