> For the complete documentation index, see [llms.txt](https://docs.nlx.ai/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nlx.ai/platform/nlx-platform-guide/ai-applications/overview.md).

# Overview

AI applications are the core of how you build, run, and deliver conversational experiences with NLX. Whether you’re creating a simple chat assistant, a hands-free Voice+™ experience, or a fully autonomous agent capable of executing complex workflows, every solution starts with an application.

This chapter introduces the different types of AI applications you can build, how they run, and how they’re deployed across channels and environments.

<figure><img src="/files/c5LYbyd8jTs8pZkyzlZB" alt=""><figcaption></figcaption></figure>

### What's an AI application?

An AI application is the deployable package that brings your conversational experience to life. Each application bundles your flows, knowledge bases, language settings, integrations, and delivery channels into a single unit that you can build, deploy, and iterate on.

Once deployed, your application becomes the backend runtime that powers conversations wherever your users interact, including web, mobile, voice, IVR, and more.

<figure><img src="/files/KRFzkYDSB6CysYNw426I" alt=""><figcaption><p>AI application in the NLX platform</p></figcaption></figure>

### How you can deploy

Deploying an application means packaging your flows, configuration, and resources into a runnable version and pushing it to the channels where it will operate.<br>

Each NLX application can be deployed in multiple ways, across channels, websites, hosted NLX Touchpoint apps, or as an MCP server, depending on where and how you want users (or other AI clients) to interact with it.

<table data-card-size="large" 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-chart-network">:chart-network:</i></td><td><strong>Channels</strong></td><td>Includes chat, voice/IVR, API, social channels, and CCaaS platforms like Amazon Connect and Genesys</td><td><a href="/pages/-M_2-fqbVTbhxtLAL9Nj">/pages/-M_2-fqbVTbhxtLAL9Nj</a></td></tr><tr><td><i class="fa-layer-plus">:layer-plus:</i></td><td><strong>Touchpoint SDK</strong></td><td>Add your AI assistant to your website or mobile app using the NLX Touchpoint SDK, including Voice+ interactions</td><td><a href="/spaces/2VnkvXtkrR2qhkVBmB1l/pages/tfr3mD2KP2eIJbZYt7gI">/spaces/2VnkvXtkrR2qhkVBmB1l/pages/tfr3mD2KP2eIJbZYt7gI</a></td></tr><tr><td><i class="fa-globe-pointer">:globe-pointer:</i></td><td><strong>Hosting</strong></td><td>Spin up an NLX-hosted Touchpoint of your app on our conversational.app subdomain. Great for testing and sharing during development</td><td><a href="/pages/RyfX8Yf1pfaG0t3ZtImk">/pages/RyfX8Yf1pfaG0t3ZtImk</a></td></tr><tr><td><i class="fa-mcp">:mcp:</i></td><td><strong>MCP Server</strong></td><td>Expose your NLX application as an MCP server, enabling clients to call your workflows, fetch data, and execute actions through Model Context Protocol</td><td><a href="/pages/a3Uki6gor35zYjasuuRx">/pages/a3Uki6gor35zYjasuuRx</a></td></tr></tbody></table>


---

# 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.nlx.ai/platform/nlx-platform-guide/ai-applications/overview.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.