1

Sign in to Agent Assist and select a project.

2

While you create the conversation profile, ensure that you select the following:

  • In the Suggestion Types field, select the Articles and/or FAQs to suggest documents from the knowledge base that are relevant to the end-user issues. When prompted to enter the details of the knowledge base, create a new knowledge base by selecting Data from the left menu.

  • In the Retrieval Method field, select Inline suggestions (API response) to enable Webex CCAI to receive the responses from Google CCAI.

  • In the Maximum Suggestions field, enter the maximum number of suggestions you want to display for each suggestion set (returned by Google CCAI to Agent Desktop) in the Agent Answers gadget.

  • If you are using Virtual Agent, select Enable virtual agent. A Virtual Agent provides conversational self-service with hand-off to human agents as necessary.

For more information, see the Google documentation.

Create a conversation profile (for non-US data center)

1

Create a Service Account through the Google IAM (Identity and Access Management) console.

2

Add the following service account admin roles: Dialogflow API admin, Service Account Token Creator, and Service Account user. The application creates the Service Account ID.

3

Install and configure the Google SDK on your system.

4

Log in to the Google Cloud Platform (GCP) CLI using the Google account user ID with the command gcloud auth login.

The user who generates the token should have the following roles: Dialogflow API Admin, Owner, Service Account Token Creator, Service Account User, and Workload Identity User.

5

Run the following command: gcloud auth print-access-token --impersonate-service-account=Service Account ID.

Use the Service Account ID created in Step 1.

6

Create the conversation profile using the REST API for Dialogflow by using any REST client:

  1. Use the method as POST.

  2. In the URL field, add the address in the following format after replacing the regionId and projectId appropriately: https://<regionId>-dialogflow.googleapis.com/v2beta1/projects/<projectId>/locations/<regionId>/conversationProfiles.

  3. In the Headers section, add the following key values for Authorization and Content-type:

    Authorization: Bearer <token generated in step 5>

    Content-type: application/json

  4. In the Body section, enter the following request body in JSON format:

    Replace the regionId, projectId, and agentId in the agent tag with actual values.

    {
    "name": "TACCXTest",
    "automatedAgentConfig": {
        "agent": "projects/<projectId>/locations/<regionId>/agents/<agentId>”
        },
    "displayName": "TACCXTest",
    "humanAgentAssistantConfig": {
        "messageAnalysisConfig": {    
            "enableEntityExtraction": true,
            "enableSentimentAnalysis": true
            }
        }
    }
    
  5. After the request is processed, you will receive the following response with the HTTP status code 200.

    Example response:

    {
    "name": "projects/projectrtp2020/locations/us-central1/conversationProfiles/QlO36mwSUa3cjg",
    "displayName": "TACCXTest",
    "automatedAgentConfig": {
    "agent": "projects/projectrtp2020/locations/us-central1/agents/40d0-aa2a-1bf453d9bf5c/environments/draft"
        },
    "humanAgentAssistantConfig": {
    "notificationConfig": {},
    "messageAnalysisConfig": {
    "enableEntityExtraction": true,
    "enableSentimentAnalysis": true
            }
        },
    "languageCode": "en-US"
    }
    

    You can get the following conversation profile URL: projects/projectrtp2020/locations/us-central1/conversationProfiles/dQlO36mwSUa3cjg.

7

Copy the conversation profile URL from the response received in Step 6 in the following format: projects/<project_ID>/locations/<location>/conversationProfiles/<profile ID>.

You can use this profile URL to create the Contact Center AI configuration on Control Hub.

What to do next

Create a Contact Center AI configuration. For more information, see the article Create a Contact Center AI configuration.