Agent AI Integration with Genesys Cloud CX

​

Definitions

​

Architecture Diagrams

​

Interaction Sequence

​

Activities on Platform

• Capture AI Agent information in Kore Data Table
• Access Custom Data and Secure Custom Data in Agent AI

​

Activities on Genesys Cloud

• Generate an Oauth ID to connect Kore Services with Genesys
• Create an Interaction Widget in Genesys for Agent AI
• Provide Interaction Widget Access to Agents
• Create a Queue in Genesys

​

Chat Setup

• Create or Update Architect Inbound Message Flow in Genesys for the Agent Queue
• Create Messenger Configuration
• Create Messenger Deployments
• Steps to start a Chat Request Simulation

​

Voice Setup

• (Optional) Install Audiohook for Voice Streaming
• Create or Update an Architect Inbound Call Flow in Genesys for the Agent Queue
• Steps to start a Voice Request Simulation

​

Prerequisites

• Genesys Administrator with access to a Genesys Cloud account with Admin rights
• Platform Administrator with access to Agent AI instance

​

AI for Service Configuration

​

Capture AI Agent Information

​

Genesys Data Table

1. Sign in to Genesys Cloud.
2. Select Collaborate / Communicate.
3. Select Menu > Orchestration > Orchestration Assets > Data Tables.
4. Select + Add to create a new Data Table.
5. Enter a relevant name, such as KoreaiAA-configuration, and then select Save.
   You must set the Reference Key Label to AgentAssist. The Interaction Widget uses this value to load the configuration data.
6. Select the pencil icon to edit a data table.
   Don’t select the data table name.
7. Select Add Field under Custom Fields to create seven custom fields to provide the AgentAssist configuration. Set the data type of all custom fields as String.
8. Add the custom fields with bot details.
9. Follow these conventions in the table for other custom fields. Use the exact names, including upper/lowercase.

​

Third-Party Configuration

• Create a record in Third Party Configuration for Agent AI Bot1, setting the Queue Identifier as Queue1.
• Create a record in Third Party Configuration for Agent AI Bot2, setting the Queue Identifier as Queue2.

​

Kore Data Table

• The system fetches AI Agent credentials based on Genesys desktop queue names. If the Genesys queue name is of the <QUEUEIDENTIFIER><QDELIMITER>XXXXX format, for example ALPHAINC_CUSTOMERSERVICE_16092024, then:
• QueueIdentifier = ALPHAINC and qDelimiter = _.
• Update the QueueIdentifier in the Kore Data Table.
• Update the qDelimiter in the Create an Interaction Widget in Genesys for Agent AI section.

​

How to create a new Data Table

1. Sign in to AI for Service.
2. Select Data > Data Tables.
3. Select New Table.
4. Enter the following details in the New Table page:
   1. Name of the Data Table (any alphanumeric name).
   2. Description of the Data Table.
   3. Columns to include in the Data Table. Select the check mark to add multiple columns. Add the following case-sensitive columns with type string: Mandatory Columns:
      • QueueIdentifier (unique identifier for the table)
      • BotId
      • ClientId
      • ClientSecret
      • AgentAssistWidgetURL
      • AudiohookEnabled
      • JWEPublicKey
      Optional Columns:
      • KvpConfig
      • Algorithm (HS256)
      • RSPrivatePem (Ignore/Not Supported)
      • isAgentAISDK
   4. Indexes for the table.
      • Index Name for reference.
      • Is Unique flag to define if the index contains unique values. (Turn on is Unique.)
      • Column & Sort Order - List of columns to include in the index; you can select multiple columns and specify the sorting order (ascending or descending) for each column. (Select QueueIdentifier with ascending order.)
   5. AI Agent Assignments (not applicable).
   6. App Assignments to let apps access data in this table.
      1. Select any app from the list, or select Create New App and enter your app name.
      2. Select the Read, Write, and Delete permissions, based on your requirement.
         You can also create new apps by selecting Data > Apps > New App in the home page:
   7. Process Assignments (not applicable).
5. Select Create to create the new data table.

​

Insert data into Data Table

1. Sign in to AI for Service.
2. Select Data > Apps.
3. Select the app with write access to the Data Table where you want to add information.
4. Copy Client ID and Client Secret of the app.
5. Create a JWT Token using the Client ID and Client Secret by following the Generating the JWT Token doc.
6. Insert the following data into the Data Table by following the Data Insert API doc. Use the JWT Token you created. API Body Payload Structure:
   {
       "data": {
           "QueueIdentifier": <Unique QueueIdentifier>,
           "BotId": <Kore BotId>,
           "ClientId": <Kore ClientId>,
           "ClientSecret": <Kore ClientSecret>,
           "AudiohookEnabled": `true` / `false`,
           "AgentAssistWidgetURL": <Kore Agent AI Widget URL>,
           "KvpConfig": <KVPs of SecureCustomData>,
           "JWEPublicKey": <Public Key assigned to Client App>,
           "Algorithm": "HS256"
       }
   }
   
   • For a single queue, the QueueIdentifier value contains one queue name (for example, Kore). For multiple queues, it includes all the queue names separated by commas (for example, Kore, KoreSupport).
   • JWEPublicKey and KvpConfig values must be JSON objects converted to strings.

​

Generate an Oauth ID to connect Kore Services with Genesys

1. Sign in to Genesys Cloud.
2. Select Collaborate / Communicate.
3. Search for OAuth.
4. Select Add Client.
5. Enter the app name and description, and select Code Authoriztion/PKCE as the Grant Type.
6. Enter token duration and add {Agent AI URL}/koreaiaa-genesys/ in the Authorized redirect URIs field.
7. Add the following list of scopes in the Scope section:
   • architect:readonly
   • conversations
   • conversations:readonly
   • integrations
   • integrations:readonly
   • messaging
   • messaging-platform
   • messaging-platform:readonly
   • messaging:readonly
   • notifications
   • user-basic-info
   • web-chat
   • web-chat:readonly

​

Create an Interaction Widget in Genesys for Agent AI

1. Sign in to Genesys Cloud.
2. Select Collaborate / Communicate.
3. Select Menu > Integrations.
4. If you haven’t created an Interaction Widget for Agent AI, install a new Interaction Widget by selecting Add integration.
5. Enter a meaningful name for the Interaction Widget, such as KoreaiAA Interaction Widget.
6. Open the Interaction Widget by selecting the name.
7. Go to the Configuration tab of the Interaction Widget.
8. In the Application URL field, enter the following structure:
   {Agent AI URL}/koreaiaa-genesys/?conversationid={{gcConversationId}}&lang={{gcLangTag}}&environment={{gcHostOrigin}}&genesysid=<genesys-oauth-Id>&x_passthru_metadata=<Token>&showWidget=true/false&sendEventsToVG=true/false&oauthgrant=pkce
   
   • x_passthru_metadata is an optional query parameter for passing custom data to Agent AI.
   • showWidget: Determines whether the Agent AI widget appears during agent transitions.
     • Set to true to display the widget for Agent 1, if Agent 1 exits and Agent 2 takes over the conversation.
     • Set to false to hide the widget during these transitions.
   • sendEventsToVG: Determines whether the system sends events to Voice Gateway to pause or resume transcriptions when agents put a call on hold or resume it. This reduces Automatic Speech Recognition (ASR) costs by avoiding transcription of hold music from Genesys.
     • Set to true to use the new Audiohook flow for transcriptions, which uses the configurations under Advanced Settings.
     • Set to false to continue using the old Audiohook flow for transcriptions.

1. For the oauthId value, use the OAuth ID from the Generate Oauth ID section.
2. Build x_metadata:
   1. Sign in to AI for Service.
   2. Select Data > Data Tables, and copy the Data Table name.
   3. Select Apps, and select one of the app names with read access.
   4. Copy the Client ID and Client Secret values.
   5. Create a JWT Token using the Client ID and Client Secret by following the Generating the JWT token doc.
   6. Generate a JSON object with the following structure, and then convert it into a URL-encoded string:
      {
       "datatable": {
         "name": <paste datatable name>,
         "token": <paste token created in previous step>,
         "qDelimiter": <Paste the special character used in the queue name to distinguish the QueueIdentifier from the remaining part of the queue name>
       }
      }
      Website for url encoding - urlencoder
      
      Reference:
   7. Copy the URL-encoded string and paste it as the x_metadata value.
3. Allow all permissions in iFrame Sandbox Options and iFrame Feature/Permission Policy: iFrame Sandbox Options: allow-forms,allow-modals,allow-popups,allow-presentation,allow-same-origin,allow-scripts,allow-downloads. iFrame Feature/Permission Policy: camera,microphone,geolocation,clipboard-write,display-capture,fullscreen. Communication Type Filtering: chat and call.

​

Provide Interaction Widget access to agents

​

Group Membership

1. Use an existing group, if your agents are already part of it. Otherwise, create a new group for Agent AI permission.
2. Name the group as KoreAA-Agents or a similar name to distinguish it.
3. Add any agent to allow them to use the Agent AI functionality. You can use multiple groups.
4. Go back to the Integrations section and open the Interaction Widget you created in the Create an interaction widget section.
5. On the Configuration tab, add access using the group you identified or created for Agent AI in the Group Filtering option. You may also use Queue Filtering (optional).

​

Custom Role/Permission

1. Sign in to Genesys Cloud.
2. Select Collaborate / Communicate.
3. Select Menu > User Management > Roles and Permissions.
4. Select Add Role to create a new role.
5. Enter a distinctive name to the role; for example, KoreaiAA Agent.
6. On the Permission tab, search for Conversation > Transcription - View, and add it (select the box):
   The Conversation permission is available only in the CX3 license.
   The Assigned Permissions view looks like the following image:
7. On the Roles and Permissions page, select the three dots at the right end of a role, and select Change Membership. Add the appropriate agents to the role.

​

Create a Queue in Genesys

1. Sign in to Genesys Pure Cloud.
2. Select Collaborate / Communicate.
3. Select Menu > User Management > Queues, or enter queues in the search bar under the Collaborate / Communicate section and press the Enter key.
4. Select Create Queue.
5. Enter/select the following details in the Create Queue page:
   • Name: Enter a unique name for the new queue.
   • Division: Select a division in which you want to place this queue.
   • Copy settings and members from (optional): Select an existing queue name, if you want to copy the settings and members from it.
   • Peer Id (optional): Enter a unique ID the system can use to identify the queue from an external platform.
6. Select Save.

​

Enabling the Audio Monitoring toggle

1. Sign in to Genesys Cloud.
2. Select Menu > User Management > Queues, or enter queues in the search bar under the Collaborate / Communicate section and press the Enter key.
3. Select a queue name.
4. Select the Voice tab.
5. Turn on the Audio Monitoring toggle. Audio Monitoring: Voice settings on a Queue have an additional Audio Monitoring option, separate from Voice Transcription. This gives you control over which features you turn on. Audio Monitoring activates in the queue only if your organization activates Audiohook Monitor.

​

Chat Setup

​

Create or Update Architect Inbound Message Flow in Genesys for the Agent Queue

1. Sign in to Genesys Cloud.
2. Go to Menu > Orchestration > Architect.
3. Select the three dots next to Flows: Inbound Call, and select Inbound Message.
4. Select +Add to create an Inbound Message Flow.
5. Enter the name and description of the inbound message flow.
6. Select Create Flow. The final architect flow looks like the following screenshot:
7. Select Publish.

​

Create Messenger Configuration

1. In Genesys Cloud, go to Menu > Digital and Telephony > Message > Messenger Configurations.
2. Select New Setup.
3. Enter a name and description.
4. Select a digital channel: Messaging, Knowledge, or Knowledge Portal.
5. Select Next.
6. In the Appearance tab, complete the following information:
   • Under Select your Supported Languages, select the Select language(s) list and choose the languages that you want to support in the Messenger interface.
     You must configure the same language in Kore AI Agent.
   • Under Select Default Language, select the Select language list and choose the default language.
   • Adjust the other settings according to your preferences.
7. Select the Apps tab and complete the following steps:
   • Under Clear Conversation, turn the toggle on. You need this for the Agent AI Conversation Summary feature to work.
   • Adjust the other settings according to your preferences.
8. Select Save New Version to create a new version.

​

Create Messenger Deployments

1. In Genesys Cloud, go to Menu > Digital and Telephony > Message > Messenger Deployments.
2. Select New Deployment.
3. Enter a name and description.
4. Under Select your Configuration, select the Select Configuration option to select a version of a messenger configuration you created in the previous step to assign to this deployment.
   • In the Assignment pane, navigate to the Messenger configuration you want to assign to the configuration, and select the name of the Messenger configuration.
   • Select the version you want to assign.
   • Select Save.
5. Under Restrict domain access, determine whether to allow all domains or restrict the domains on which you want to deploy the snippet.
   • To allow all domains, select Allow all domains. (Use this option for testing and development purposes.)
   • To restrict domains, enter a domain and select Add Domain. You can add multiple domains to the list. Restrict domains to prevent unauthorized usage of your snippet from unknown domains. If you restrict a domain, Messenger doesn’t run on that website and rejects API requests from that domain.
6. Under Select your Architect Flow, select the inbound message flow you created in the previous steps.
7. Select Save. The Messenger Deployments page now displays the snippet and the deployment key.
8. Copy the Messenger snippet and deploy the Messenger snippet to your website. If you are building a custom Messenger, copy the deployment key.
   The Messenger window appears after the website page loads.

​

(Optional) Install Audiohook for Voice Streaming

1. In Genesys Cloud, go to Collaborate / Communicate > Menu > IT and Integrations > Integrations.
2. Enter audiohook in the search bar. Audiohook integration requires specific configuration values to support Agent AI configuration.
3. Install a new audiohook app by selecting Integrations in the upper-right corner.
4. Open the Audiohook, and go to the Configuration tab.
   1. Channel value must be both.
   2. The Connection URI format must be similar to wss://{Voice Gateway}/audiosocket/genesys/?sipuri=xxx&token=xxx&botId=xxx&accountId=xxx&agentassist=true.
   • Add multiBot=true parameter to it to use multiple Agent AI bots with different queues.
   • Configure the SIP of any of the bots inserted in the Data Table.
   • Get the Voice Gateway host name from the corresponding environment you use at SaaS or on-prem.
5. Follow these steps to get the Connection URL:
   1. Go to Agent AI > Flows & Channels > Voice Gateway > SIP Numbers > Configure SIP Trunk.
   2. Select Agent AI in the Product Selection section.
   3. Select Genesys Audiohook in the Select the SIP Trunk connection method dropdown list.
   4. Select Copy next to the Connection URL field.
6. Add the following details in the Advanced tab:
   {
     "environment": <genesys-environment(For example: mypurecloud.com)>,
     "oauthClientId": <genesys-oauth-id>,
     "koreDomainURL": <Agent AI URL>,
     "oauthClientSecret": <genesys-oauth-secret>,
     "sendEventsToVG": `true`,
     "botId": <Bot-ClientID>,
     "token": <JWT-token-created-in-previous-step-using-Bot-ClientID-and-ClientSecret>
   }
   
   Create an OAuth using the Client Credentials grant type, and use the resulting Client ID and Client Secret for configuration.
   
7. Add credentials in the Credentials tab.
8. Use the ClientID and ClientSecret of the AI Agent you used while configuring the Audiohook. The system uses these credentials to validate the audio stream signature.
9. Select Save.

​

Create or Update Architect Inbound Call Flow in Genesys for the Agent Queue

1. In Genesys Cloud, go to Menu > Orchestration > Architect.
2. Select +Add to create an Inbound Call Flow.
3. Select Create Flow. The final architect flow looks like the following screenshot:

​

Access Custom Data and Secure Custom Data in Agent AI

• Welcome Events in the Agent AI configuration page
• Dialog Tasks in the Agent AI automation page

var cd = JSON.parse(context.sessiinternalMetaDataon.UserContext.customData.internalMetaData);

print(cd.\<key\>);

​

Post Installation Setup

1. Sign in to Genesys Developer Applications.
   To start chat simulation, you must have access to the Genesys Developer portal (an account with Genesys).
2. Select Web messenger, select the Deployments, and then select Start Chat to initiate the chat request.
3. Enter a message on the Message Us window, and then select the Send icon.
4. Turn on the On Queue toggle on the upper-right corner of the page. A new chat notification appears on the Genesys Agent Desktop.
5. Accept the conversation by selecting Answer on the left panel.
6. Select the Interaction Widget icon to view the Agent AI widget.

1. In Call Routing, assign the Architect flow you created in a previous step to a Genesys phone number.
2. Initiate a call using this Genesys phone number. A new call notification appears on the Genesys Agent Desktop.
3. Accept the conversation by clicking Answer on the left panel.
4. Select the Interaction Widget icon to view the Agent AI widget.

​

Set the default contextual panel to Kore Agent AI Interaction Widget

1. In Genesys Cloud, select Menu > Digital and Telephony > Interaction Assets > Panel Manager. This opens the Default Contextual Panel.
2. Select the interaction widget name in both Voice and Web Messaging field dropdown lists (refer to step-4 of Create an Interaction Widget in Genesys for Agent AI).
3. Select Save.
   Reload the Genesys Agent Desktop before testing this latest change.

​

Support for Agent Transfer

• Cold Transfer: A cold transfer occurs when one agent hands over a conversation to another, and it’s applicable across Voice, Chat, and Email channels. The system generates a new conversation summary for the receiving agent and adds it to Agent-1’s Assist tab, along with feedback options. Agent-2 can modify the summary feedback for Voice and Email channels.
• Warm Transfer: A warm transfer is like a conference call between two agents, applicable to Voice and Chat channels. During the transfer, Agent-2 can modify the summary feedback. However, the Run, Override, Send, Copy, Terminate, Restart, and List View buttons remain unavailable until Agent-1 disconnects from the call.

​

Switch to Agent AI SDK (Optional)

​

Kore Data Table Change

1. Go to the Kore Data Table.
2. Select on the name of the Data Table.
3. Add a new column to the existing data table as isAgentAISDK and data type as string.
4. Select Create/Update (for existing table configuration).

​

Insert or update data into Data Table

    {
        "data": {
            "QueueIdentifier": <Unique QueueIdentifier>,
            "BotId": <Kore BotId>,
            "ClientId": <Kore ClientId>,
            "ClientSecret": <Kore ClientSecret>,
            "AudiohookEnabled": "true" / "false",
            "AgentAssistWidgetURL": <Kore Agent AI Widget URL>,
            "KvpConfig": <KVPs of SecureCustomData>,
            "JWEPublicKey": <Public Key assigned to Client App>,
            "Algorithm": "HS256",
           "isAgentAISDK": "True"
        }
    }