# Amazon Connect

### Prerequisites

Assigning this channel to an application requires both a one-time integration of Amazon Lex and Amazon Connect in your NLX workspace. Lex provides the natural language processing (NLP) layer that interprets user input, while Connect manages the telephony or chat experience.&#x20;

<a href="../../../integrations/types/nlp-engines/amazon-lex" class="button primary">Integrate Amazon Lex</a>

<a href="../../../integrations/types/channels/amazon-connect" class="button secondary">Integrate Amazon Connect</a>

For each new application in your workspace, complete the following setup. Afterward, all future deployments of your app will automatically sync to your Connect instance without additional configuration.

### Add channel to app

1. Select *Configuration* tab of your application&#x20;
2. Choose *+ Add channel* under *Delivery* section > Choose Amazon Connect
3. Choose your Amazon Connect workspace integration from the *Integration* dropdown

> Optional:
>
> * *Custom conversation timeout:* Toggled OFF by default. Terminates call after defined time (in minutes) has passed when no user inputs are received
> * *Amazon Connect instance ID*
> * *Fulfillment Lambda ARN*: If provided, this overrides the [*Fulfillment Lambda ARN for the organizational-level Amazon Connect integration*](https://docs.nlx.ai/platform/nlx-platform-guide/integrations/types/channels/amazon-connect)
> * *Region*: The AWS region your Connect instance is deployed through

4. Click *Create channel*
5. Create an [application build and deploy it](https://docs.nlx.ai/platform/nlx-platform-guide/setup#deployment)

### Import contact flow into Amazon Connect

1. Within NLX, go to your application's *Configuration* tab. Click the Amazon Connect channel added previously
2. Under *Setup instructions,* click *Download contact flow* &#x20;
3. A JSON ﬁle will be downloaded to your computer
4. Log in to your Amazon Connect instance > Select the *Access URL* under *Access information* in your Amazon Connect console
5. Select *Contact flows* from the menu > Click the *Create contact flow* button
6. Under the new contact ﬂow, click the down arrow to the right of *Save* and select *Import flow (beta)*&#x20;
7. Click the *Select* button to locate the JSON template downloaded to your computer. Select *Import*
8. The JSON file is imported into your Amazon Connect instance, and the contact flow may look something like this:

![Contact flow in Amazon Connect instance](https://2737319166-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FHCxYxhIU0Bqkjj942mGk%2Fuploads%2FmYysMAzh2OQwgNU2mgqa%2FAmazonConnectBetaFlow.jpg?alt=media\&token=1815e936-6b65-4cf1-afec-31625b7d80c7)

### Configure Amazon Connect to use your NLX app

1. Log in to your AWS account and go to the [*Amazon Connect dashboard*](https://console.aws.amazon.com/connect/home)
2. Select your instance, then choose *Flows* from the *Overview* menu.&#x20;
3. From the *Bot* dropdown, select your application's name followed by an *\_AmazonConnect* suﬃx (e.g., *MyApplication\_AmazonConnect*)
4. Under the *AWS Lambda* section, use the *Lambda Functions* dropdown to select the *AWS Lambda Function* created by your NLX integration

### Optional: Assign a phone number

1. Open the *Channels* menu in Amazon Connect and choose *Phone numbers*
2. Click *Claim a Phone Number* > Select a Toll-free or Direct Inward Dialing (DID) number
3. Assign the phone number to the Contact Flow created


---

# 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/ai-applications/deployment/managing-channels/creating-an-amazon-connect-channel.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.
