# Overview

### What's a Flow?

A flow represents the structured path a conversation follows to fulfill a user’s intent. Whether that’s answering FAQs, completing a specific task, or guiding the user toward an action. Each flow combines logic, prompts, and responses to handle the specific purpose behind an interaction.

Flows are created and organized visually in the Canvas, where you can drag, drop, and connect nodes to map out each step of a conversational experience. From capturing user inputs to triggering API calls, every node plays a role in guiding the user toward their goal.

<figure><img src="https://2737319166-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FHCxYxhIU0Bqkjj942mGk%2Fuploads%2FCcXzQr4nX3MD1aZFd7iG%2Fimage.png?alt=media&#x26;token=d39bb664-0687-4670-bd50-1f5a407a6908" alt=""><figcaption></figcaption></figure>

Once a flow is attached to an application and deployed as part of a build, that application can execute the flow and automate the corresponding task. A single application may include multiple flows to cover a range of intents, while an individual flow can also be shared across multiple applications in your workspace for greater flexibility and reuse.

To access, click *Resources* in your workspace menu and choose *Flows.*

{% @arcade/embed flowId="UI5SxcWT7aFV5DhjJA19" url="<https://app.arcade.software/share/UI5SxcWT7aFV5DhjJA19>" %}

## Build smarter flows with NLX

Flows are the backbone of AI applications. Learn how to design, organize, and optimize conversations, from defining variables and managing state to customizing your flow’s appearance and performance.

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-arrow-progress">:arrow-progress:</i></td><td><strong>Flows &#x26; variables</strong></td><td>Understand how flows and dynamic information types work</td><td><a href="overview/flows-and-variables">flows-and-variables</a></td></tr><tr><td><i class="fa-arrows-spin">:arrows-spin:</i></td><td><strong>Turns &#x26; state</strong></td><td>Recognize fundamental concepts in AI conversations</td><td><a href="overview/turns-and-state">turns-and-state</a></td></tr><tr><td><i class="fa-palette">:palette:</i></td><td><strong>The Canvas</strong></td><td>Become familiar with the controls of your powerful flow builder</td><td><a href="overview/canvas">canvas</a></td></tr><tr><td><i class="fa-gears">:gears:</i></td><td><strong>Flow settings</strong></td><td>Learn about setup and advanced options for controlling the flow</td><td><a href="overview/setup">setup</a></td></tr><tr><td><i class="fa-stop">:stop:</i></td><td><strong>Nodes</strong></td><td>Understand the basic building blocks for assembling flows</td><td><a href="overview/nodes">nodes</a></td></tr><tr><td><i class="fa-paintbrush">:paintbrush:</i></td><td><strong>Flow appearance</strong></td><td>Learn simple tricks to customize your flow and keep things organized</td><td><a href="overview/stay-organized">stay-organized</a></td></tr></tbody></table>


---

# 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.nlx.ai/platform/nlx-platform-guide/flows-and-building-blocks/overview.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.