Amazon Connect Integration with Kore using Amazon External Voice Connector (Voice Automation)

​

Architecture Diagram

​

Prerequisites

• External voice transfer connectors per account with an AWS Connect instance turned on.
• A Kore voice AI agent trained with few use cases.

​

Set up Instructions

​

1. Enabling External Voice Transfer in Amazon Connect

• Service Quota Increase: Submit a Service Quota Increase request to Amazon Connect. Amazon Connect turns on this feature only after it approves your request.
• Accessing the Option: After approval, the External voice systems option appears in your Amazon Connect console.

​

2. Creating an External Voice Transfer Connector

• Navigate to Connector Creation: Select the External voice systems option to open the connector creation screen.
• Connector Configuration:
  • Name: Enter a name for the connector.
  • Connector destination type: Select AudioCodes from the dropdown list.
  • Voice system type: Select one or more options. This selection doesn’t affect functionality.
  • Encryption: Select Disabled.
  • Logging: Select both options to view the corresponding logs in Connector Logs.
• Host and Port Details: After creation, the connector configuration displays the IP address of the host, the protocol, and the port. This port corresponds to your Voice Gateway environment.
• The final configuration appears as shown in the following screenshot:

​

3. Configuring the Amazon Connect Flow

• Add Transfer to Phone Number node: In your Amazon Connect flow, add a Transfer to phone number node.
• Select External Voice System instead of entering a phone number.
• Attach the connector you created in the previous step.
• Set the Resume flow after disconnect option to Yes. This ensures that after the call ends with the third-party system (Voice Gateway), the call transfers back to Amazon Connect (facilitating a continuous flow and correlation between Amazon Connect and the Kore system).

​

4. Configuring Contact Center AI (Kore Side Configuration)

• Create New Configuration: In CCAI, create a new configuration (or use an existing one).
• Allowlist IP Address: Add the IP address that Amazon Connect provides to the allowlist. This IP address is essential for allowing communication from Amazon Connect to Kore. Check with Amazon Connect documentation or Support for the details on this IP address.
• DID Number: Enter the Direct Inward Dialing (DID) number you specified in the Transfer to phone number node in the previous step).
• Attach to Start Flow: Once the configuration is complete, attach this number to the relevant Experience Flow within Kore.

​

End-to-End Call Flow

1. A customer calls the Amazon Connect number.
2. The Amazon Connect flow transfers the call to Voice Gateway via the external voice connector.
3. CCAI handles the call. To view the call details, go to the CCAI Dashboard > Interactions section.
4. After the interaction, the system transfers the call back to Amazon Connect.

​

Metadata Passing from Kore to Amazon Connect (Additional Feature)

• API Gateway
• Lambda function
• DynamoDB Table
• CloudWatch (for debugging)

​

Architecture

1. Create a DynamoDB table with contactId (Amazon Connect Contact Id) as a partition key.
2. Create an API Gateway and call it from outside AWS via Dialog Task > Service Node in CCAI, before agent transfer, to store data in the DynamoDB table.
3. To call this API, the system must pass the Amazon Connect contact ID as one of the query parameters. The system retrieves this ID from the SIP headers data that Amazon Connect sends to Kore.
4. Create two Lambda functions — one for the API Gateway business logic and the other for its authentication.
5. In the Amazon Connect flow, invoke another Lambda function to extract these metadata saved in DynamoDB in the last step.
6. These metadata values are then set as contact attributes within the flow.

​

AWS Side Configuration

​

Create a DynamoDB Table

​

Create Three Lambda Functions

1. koreStoreSessionMetadata: Use this Lambda function to expose an API Gateway (Trigger) to get the metadata from platform and store it in the DynamoDB table. Copy and deploy the code from this link.
2. AuthenticateBeforeStoringInDynamoDB: Use this Lambda function to add an authentication layer (Authorizer) to the API Gateway in the previous Lambda function (koreStoreSessionMetadata). Copy and deploy the code from this link.
3. koreRetrieveSessionMetadata: Amazon Connect Contact Flow invokes this Lambda function after the call disconnects from Kore and returns to Amazon Connect. This Lambda function returns all the metadata stored in the DynamoDB table using the first Lambda. Copy and deploy the code from this link.

​

Create an API Gateway

1. Create a REST API Gateway with the default configuration:
2. Create an API resource with the Resource path as /kore-metadata, and then select Create resource:
3. Create an API Method with the following details:
   • Method type: POST
   • Integration type: Lambda function (koreStoreSessionMetadata)
   • Turn on the Lambda proxy integration toggle.
   • Select the Lambda function (koreStoreSessionMetadata).
   • Select Create Method.
4. To authenticate this API Gateway, you need Authorizers. Create a new Authorizer with the following details:
   • Authorizer name: koreClientAuth
   • Authorizer type: Lambda
   • Lambda function: AuthenticateBeforeStoringInDynamoDB
   • Lambda event payload: Select Token
   • Token source: authorizationToken
   • Token validation - optional: Enter the value you want to use as Token for the API authentication. You need the same value to store in the Env Variable of AuthenticateBeforeStoringInDynamoDB Lambda function with the key as AUTH_TOKEN.
   • Select Create authorizer.
5. After creating the koreClientAuth authorizer, add this as part of authentication for the API resource and method.
   • Select Edit method request.
   • Select Token authorizers > koreClientAuth under Authorization.
   • Select Save.
6. Select Deploy API.

​

Modify the Contact Flow

1. Name this flow as TransfertoKore&MetadataPassing. (This name appears during the Agent AI integration step.)
2. Add an AWS Lambda function node after the Transfer to phone number node.
3. In the AWS Lambda function:
   • Select the Invoke Lambda function (koreRetrieveSessionMetadata), added in the last step.
   • Add a parameter:
     • Destination Key: contactId (enter this name)
     • Value: set dynamically
       • Namespace: System
       • Key: Contact id
   • Response Validation: JSON
   • Save the configuration.
4. Add one Set contact attribute node. In this node:
   • Set attributes on: Current Contact
   • Add another attribute
     • Namespace: User defined
     • Key: customData
     • Value to be Set dynamically
       • Namespace: External
       • Key: body
   • Save the configuration.
5. Connect all the nodes. You can add a Play prompt node to check if there is any error in the flow.
6. Save and Publish the flow. The modified Amazon Connect flow appears as shown in the following screenshot:

​

Kore Side Configuration

​

In CCAI

1. Start Flows
   1. Open Conditional Flow.
   2. Add the following code snippet in a Script node immediately after the Start node:
      setCallFlowVariable('sipHeaders',
      context.BotUserSession.channels[0].handle.sipHeaders); var
      headers = getCallFlowVariable('sipHeaders');
      userSessionUtils.put('sipHeaders', headers);
      
   3. Select Test to test the flow.
   4. Identify the Automation bot in Conditional Flow. Use it in the next step when configuring the Botbuilder.
2. Agent Transfer
   1. Go to Settings > Integrations > Agent Transfer > Voice.
   2. Select SIP Transfer.
   3. Select SIP BYE from the SIP Transfer Method list.
   4. Select Save to save the configuration.

​

In Botbuilder

1. Open the Agent Transfer dialog task.
2. Add a Script node and paste the following code to extract contactId (Amazon Connect contact Id) from the SIP headers:
   try{
   var headers = context.session.UserSession.sipHeaders;
   if(headers){
        var contactId = headers.find(o => o.name ===
   'X-Amzn-ConnectContactId');
        if(contactId){
            BotUserSession.put("ContactId", contactId.value);
   }
   }
   }catch(err){
   koreDebugger.log("Error is:"+err);
   }
   
3. Add a Service node immediately after the Script node to make a REST API request to the API Gateway you configured in AWS in the earlier steps.
4. Select Define Request in the Service node.
5. Add the Request URL: Add the API Gateway URL with contactId as query parameter. Get this by accessing your first Lambda function (“koreStoreSessionMetadata_S”) > Configuration > Triggers.

• Method: POST
• Headers:
  • Content-Type: application/json
  • authorizationToken: “abc123” (Add your token)
• Body:
  • Add your metadata Example:

{"x_metadata":"Hello from Kore", "kore-instanceSessionId":"{{context.session.BotUserSession.lastMessage.messagePayload.instanceSessionId}}"}

• Save the configuration.
• Publish the bot.

​

Validate Your Metadata

1. Sign in to Amazon Connect.
2. Select Analytics and optimization > Contact search.
3. Filter the results by contact ID.
4. When you open a contact’s details, the metadata appears as contact attributes.

​

Passing Metadata as Custom Data to Agent AI

​

Modify the Amazon Connect flow