Amazon Connect

​

How it works

1. Hand off the conversation to GenerativeAgent through your Amazon Connect Flows.
2. GenerativeAgent handles the conversation using Lambda functions to communicate with ASAPP’s APIs, and respond to the caller using AWS’s Text to Speech (TTS) service.
3. Return control back to your Amazon Connect Flow when:
   • The conversation is successfully completed
   • The caller requests a human agent
   • An error occurs

​

Before you Begin

• Get your API Key Id and Secret
  • Ensure your API key has been configured to access GenerativeAgent APIs. Reach out to your ASAPP team if you need access enabled.
• Have an existing Amazon Connect instance:
  • Have claimed phone numbers.
  • Access to an Amazon Connect admin account.
• Have a AWS administrator account with the permissions for the following:
  • Creating/managing IAM roles/policies: create a policy permitting list/read operations on the Kinesis Video Streams associated with the Amazon Connect Flow
  • Managing Amazon Connect instance
  • Create/manage Lambda functions
  • Create/manage CloudWatch Log Groups
  • Create/manage ElastiCache for Valkey
  • Create/manage VPC
• Be familiar with AWS including Amazon Connect, IAM roles, and more:
  AWS Components

• Receive the GenerativeAgent Connect Flow and Prompts from your ASAPP team.

​

Step 1: Set up your AWS Account and Amazon Connect instance

​

Provide a dedicated VPC

• To use an existing VPC: Verify it has at least two subnets in different Availability Zones, and that the subnets are private and isolated (not connected to the Internet).
• To create a new VPC: In the AWS Console, go to VPC > Your VPCs, click Create VPC, and follow the prompts to set up a VPC with at least two private isolated subnets in different Availability Zones.

​

Configure your Amazon Connect instance

1. Navigate to Live Media Storage
   • In the AWS Console, navigate to Amazon Connect and select your Amazon Connect instance by clicking on the Instance alias.
   • On the left menu, go to Data storage > Live Media Storage.
2. Enable Live Media Streaming
   • Under Data Storage options, enable Live Media Streaming.
3. Set Retention Period
   • Set a retention period of at least 1 hour.
4. Save the Kinesis Video Stream Instance Prefix
   • Copy the Kinesis video stream instance prefix; you will need this when you Configure IAM Roles and Policies.

​

Create security groups

1. Create all three security groups
   • In the AWS Console, navigate to VPC > Security Groups.
   • For each of the following, click Create security group, using these names (or similar):
     • ValkeyElastiCacheSecurityGroup
     • PullActionLambdaSecurityGroup
     • PushActionLambdaSecurityGroup
   • Associate each security group with your VPC.
   • Save the security group IDs for later use.
2. Configure security group rules
   • Valkey ElastiCache security group:
     • Inbound rules:
       • Allow TCP traffic on port 6379 from the PullAction Lambda security group.
       • Allow TCP traffic on port 6379 from the PushAction Lambda security group.
     • Outbound rules:
       • No outbound rules are required. Remove any default outbound rules.
   • PullAction Lambda security group:
     • Outbound rules:
       • Allow TCP traffic on port 6379 to the Valkey ElastiCache security group.
       • Remove any other default outbound rules.
   • PushAction Lambda security group:
     • Outbound rules:
       • Allow TCP traffic on port 6379 to the Valkey ElastiCache security group.
       • Remove any other default outbound rules.

​

Create the Valkey ElastiCache

1. Create a subnet group
   • In the AWS Console, navigate to ElastiCache > Subnet groups.
   • Click Create subnet group.
   • Enter a name and description for your subnet group (e.g., ValkeySubnetGroup).
   • Select your VPC.
   • Add both of your private isolated subnets (each in a different Availability Zone) to the group.
   • Save the subnet group.
2. Create a Valkey ElastiCache
   • In the AWS Console, navigate to ElastiCache.
   • In the left menu, select Valkey caches.
   • Click the Create cache button at the top right.
3. Configure Settings 3.1 Configuration
   • Engine: Select Valkey.
   • Deployment option: Choose Design your own cache.
   • Creation method: Select Cluster cache.
   • Cluster mode: Set to Disabled.
   • Cluster info: Enter a name (e.g., asapp-generativeagent), up to 40 characters.
   • Location: Choose AWS Cloud.
   • Multi-AZ: Leave Enabled.
   3.2 Cache settings
   • Engine version, Port, Parameter groups: Leave default values.
   • Node type: For testing, select cache.t4g.micro. Adjust sizing based on your expected call volume before production.
   • Number of replicas: Set to 1.
   3.3. Connectivity
   • Subnet group: Choose the existing subnet group you created previously.
   3.4. Availability Zone placements
   • Availability Zone placements: Select No preference.
   Click Next to proceed to Advanced settings.
4. Configure Advanced Settings 4.1 Security
   • Encryption at rest: Enable
   • Encryption in transit: Disable
   • Selected security groups: Click Manage and select the security groups created earlier in the Create security groups section.
   • Backups: Uncheck Enable automatic backups.
   • Maintenance: Leave default options.
   • Logs: Leave default options.
   Click Next to review your configuration.
5. Review and Create
   • Review all settings.
   • Click Create to provision your Valkey Cache.
   Once created, save the Primary endpoint—you will use this value as PRIMARY_VALKEY_HOST and PRIMARY_VALKEY_PORT when configuring your Lambda functions.
   

​

Step 2: Create Lambda functions to call GenerativeAgent

• Engage
• PushAction
• PullAction

​

Engage Lambda Function

​

PullAction Lambda Function

​

PushAction Lambda Function

​

Step 3: Configure IAM Roles and Policies

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "ReadAmazonConnectStreams",
            "Effect": "Allow",
            "Action": [
                "kinesisvideo:GetDataEndpoint",
                "kinesisvideo:GetMedia",
                "kinesisvideo:DescribeStream"
            ],
            "Resource": "arn:aws:kinesisvideo:*:[customer-account-id]:stream/[kinesis-video-streams-prefix]*/*"
        },
        {
            "Sid": "ListAllStreams",
            "Effect": "Allow",
            "Action": "kinesisvideo:ListStreams",
            "Resource": "*"
        }
    ]
}

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "Stmt1",
            "Effect": "Allow",
            "Action": [
                "lambda:InvokeFunction"
            ],
            "Resource": [
                "[lambda-pushaction-arn]"
            ]
        }
    ]
}

​

Step 4: Add Prompts and the GenerativeAgent Flow Module

​

Upload the Prompts

1. Download the prompt files Download the required .wav prompt files from the following repository: Prompt audio files
   Copy

   Ask AI

     asappBeepBop.wav
     asappSilence1second.wav
     asappSilence400ms.wav
   

2. Upload and name each prompt in Amazon Connect In your Amazon Connect instance, navigate to Routing > Prompts. For each .wav file:
   • Click Add prompt.
   • Upload the file.
   • When prompted for the name, enter the file name without the .wav extension:
     Copy

     Ask AI

       asappBeepBop
       asappSilence1second
       asappSilence400ms
     

3. Save the prompt ARNs After uploading each prompt, save the ARN for each prompt. You will need these ARNs when editing the GenerativeAgent Flow Module JSON in the Create GenerativeAgent Flow Module section.

​

Create GenerativeAgent Flow Module

1. Download the Module JSON
   • Download the ASAPPGenerativeAgent.json flow module json from the repository: ASAPP GenerativeAgent Flow Module
2. Edit the Module JSON Open the .json file and update the ARNs to reference your own Lambda functions:
   • Replace the ARN for the Engage Lambda function with the ARN you created in Step 2: Engage.
   • Replace the ARN for the PullAction Lambda function with the ARN you created in Step 2: PullAction.
   • Locate the section with "Identifier": "Wait1sPrompt" and, within its "Parameters", replace the "PromptId" string value with your asappSilence1second prompt ARN.
   • Locate the section with "Identifier": "Wait400msPrompt" and, within its "Parameters", replace the "PromptId" string value with your asappSilence400ms prompt ARN.
   • Locate the section with "Identifier": "PlayBeepBopShort" and, within its "Parameters", replace the "PromptId" string value with your asappBeepBop prompt ARN.
3. Import the Module
   • In your Amazon Connect instance, navigate to Routing > Flows > Modules.
   • Click Create flow module.
   • Expand the Save dropdown and select Import.
   • Upload your edited .json file and click Import.
4. Verify the Module
   • Ensure the imported module appears in your list and references the correct Lambda ARNs.

​

Invoke the GenerativeAgent Flow Module

1

Configure Contact Attributes

Before invoking the module, you must set up the required contact attributes:

1. Add a “Set contact attributes” block to your flow
2. Configure the following attributes:

Contact Attribute	Required	Description
ASAPP_companyMarker	Yes	Your company’s unique identifier in GenerativeAgent
Custom attributes	No	The additional attributes to pass to GenerativeAgent for the task to enter and additional input variables

The ASAPP_companyMarker is provided by ASAPP along with your API credentials. Contact your ASAPP team if you need this value.

Mapping Custom Attributes

2

Invoke the GenerativeAgent Flow Module

Create an “Invoke module” block and select the GenerativeAgent Flow Module. This is where the conversation is handed off to GenerativeAgent.

Within the GenerativeAgent Flow Module, the flow will use the various components you created in previous steps to engage ASAPP’s GenerativeAgent to the end user.Once the conversation is complete, GenerativeAgent will exit the Module and return control to your flow.

3

Handle the result

The GenerativeAgent Flow Module will exit for one of four reasons, and will output the ASAPP_Disposition contact attribute with one of the following values:

• transferToAgent: when the conversation needs to be transferred to an agent
• transferToSystem: when the conversation needs to be transferred to an external system
• disengage: when the conversation is completed
• error: when an error has occurred

4

Map output Variables

After importing the Flow Module, you may want to extract transferVariables from the system transfer from GenerativeAgent for use in your flow.

As of now, only transferVariables from system transfer are supported.

To use the transferVariables in your flow:

• In the imported Flow Module, locate the block named ExtractOutputVariables.
• For each output variable, specify the key as $.External.outputVariables.<variableName> where <variableName> is the name of the output variable you want to extract.
  • As an example, if the transfer variable is CustomerAccountNumber, the key would be $.External.outputVariables.CustomerAccountNumber.
• Save the flow.
• In the flow invoking the GenerativeAgent Flow Module, the variables are available in the flow as contact attributes. Use them in your flow as needed.

​

Step 5: Engage GenerativeAgent

1. You are handed off to GenerativeAgent
2. GenerativeAgent responds appropriately to your inputs
3. You are returned to your flow when the conversation ends

​

Next Steps