# Touchpoint

<figure><img src="/files/RidKNL3RL6a5izEqHbVj" alt=""><figcaption></figcaption></figure>

### Overview

Touchpoint is a drop-in conversational user interface (UI) and Software Development Kit (SDK) designed to seamlessly integrate conversational AI into web and mobile applications. It provides native support for text-based chat and voice interactions — as well as Voice+™, NLX's patented multimodal technology that synchronizes voice with digital assets.

{% columns fullWidth="false" %}
{% column %}

<figure><img src="/files/2yam7zQdPQLyFlX3pLYI" alt=""><figcaption></figcaption></figure>
{% endcolumn %}

{% column width="33.33333333333333%" %}

<figure><img src="/files/ViHYRejsTNfL7gcoIN1k" alt=""><figcaption></figcaption></figure>
{% endcolumn %}

{% column width="33.33333333333333%" %}

<figure><img src="/files/KakzxG8nITTmHk1F2NDX" alt=""><figcaption></figcaption></figure>
{% endcolumn %}
{% endcolumns %}

<p align="center"><mark style="color:$info;">Visual examples of Touchpoint on mobile screens</mark></p>

#### Design philosophy

The future of human-computer interaction is conversational. As applications evolve, user expectations are shifting from static menus to "conversation-first" experiences. Touchpoint enables this future today.

Unlike a traditional customer service chatbot that lives in a silo, NLX Touchpoint is a rich multimodal interface. It serves as a dynamic layer on top of your application, allowing users to interact via text or voice while controlling the digital elements on their screen and vice versa. It is completely agnostic of any industry, vertical, or use case and is equally capable of powering a retail checkout assistant, a healthcare intake form, or a banking support agent.

### Supported channels

{% content-ref url="/pages/n0ub81I8dUAA9r4HJzig" %}
[Chat](/platform/developers/conversation-sdk/examples/chat.md)
{% endcontent-ref %}

{% content-ref url="/pages/C5abRospToM3LZoDtjFs" %}
[Voice](/platform/developers/conversation-sdk/examples/voice.md)
{% endcontent-ref %}

{% content-ref url="/pages/wPqGhGwfQWfDpDGyPRuf" %}
[Voice+™](/platform/developers/conversation-sdk/examples/voice+-tm.md)
{% endcontent-ref %}

### Key features

<details open>

<summary>Drop-in installation</summary>

Get up and running in minutes using a simple HTML script tag or a standard NPM package.

</details>

<details>

<summary>Themable</summary>

Comes with polished, accessibility-compliant defaults that can be extensively branded to match your design system.

</details>

<details>

<summary>Responsive web and mobile support</summary>

Automatically adapts to desktop, tablet, and mobile form factors, including full-screen and headless modes.

</details>

<details>

<summary>Visual modality support</summary>

Goes beyond text bubbles by rendering rich UI elements (cards, carousels, date pickers) in response to both chat and voice commands.

</details>

<details>

<summary>Voice+ support</summary>

It supports NLX's signature Voice+ technology out-of-the-box.

* *Voice drives digital:*\
  A user speaking on the phone or to the website can trigger action on a connected device such as navigation or form completion.
* *Digital drives voice:*\
  On-screen interactions can trigger spoken responses or IVR logic.

</details>

<details>

<summary>Built-in support for agent escalation</summary>

Natively handles the UI state changes required when handing off from an AI assistant to a human agent.

</details>


---

# 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/developers/conversation-sdk/touchpoint.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.