How to configure Voice Agents

Introduction

Voice Agent is a powerful tool that allows automated responses and routes customers' and your team’s queries via voice AI assistance. Voice Agents can be added via the Voice Bot integration in WMS. There are several Voice Agent integration types:

• Generative AI let you create highly interactive and intelligent voice agent without any coding expertise. By providing specific instructions, the AI model generates dynamic, context-aware responses that enhance user engagement. You can also create easily incorporate custom functions to interact with third-party servers, allowing your bot to perform actions like fetching real-time data, updating records, or triggering external processes during a conversation. This option doesn’t require coding experience.

• Webhooks and AWS SQS allow you to take full control over your voice agent sessions. These options are ideal if your voice agent requires custom handling of conversations; you can build a service to analyze events and generate responses.

• Dialogflow CX is a versatile AI platform, which is great at handling natural language and managing conversations, even when they get a bit complicated. It is good for automating customer interactions, handling queries, and passing customers to agents when needed, especially in cases where you have clear predefined use cases of customer interactions, where the scenarios of communication with customers are generally the same.

• OpenAI Assistant connects your voice agent to OpenAI’s language models, which lets to handle complex conversations and provide natural responses to user queries. With OpenAI’s advanced AI capabilities, your Voice Bot can understand context, manage dialogues, and deliver personalized interactions.

Use Cases

Voice agents can be used in a variety of ways. Here are some examples: 

• Shop assistance: assisting in finding products, checking availability, or making recommendations based on their interests.

• Order processing and tracking: helping to place orders and provide updates on delivery status.

• Call centers: handling routine calls and reducing wait times, so that human agents can focus on more complex issues.

• Customer service: answering common questions of the customers, providing account information, or helping with troubleshooting over the phone.

• Language support: communicating with customers in multiple languages to address queries of a more diverse audience.

• Collecting feedback: gathering customer reviews or feedback through voice interactions to improve services.

Step 1. Create Voice Agent

To create a voice agent, proceed with the following steps:

• Navigate to WMS -> PBX -> Integrations -> Cloud integrations -> Voice Bots:
  
  

• Click Add New Voicebot:
  
  

• Enter voice agent name

• Enter First message (optional)

• Select the integration type for processing events:

  • Generative AI

  • Webhook

  • AWS SQS

  • Dialogflow CX

  • OpenAI Assistant

• Fill out the necessary fields depending on the selected integration type (see instructions below)
  
  

• Add Tools:
  Tools allow a voice agent to execute specific tasks during a call. By integrating tools, you can align your voice agents with your existing workflow. See the list of available tools below:

  • Transfer: allows to transfer a call to an agent or route via Dialplan

  • Delegate: gives possibility to delegate user’s request to another voice agent

  • Hangup: allows the voice agent to end a call by himself it the call is considered finished

  • Wait: allows to analyze the the user’s response and wait for more input if the response was incomplete

  • Third-party Function: gives possibility to integrate voice agent with various API options

To add a tool:

1. Click Add Tool -> choose the necessary option:
   

2. Fill out the necessary details:

• Configure Advanced Configuration:

  • Interruption Detection: if enabled, customers can interrupt the agent and the system will stop the playback of the voice agent's response. By default, the option is disabled.

  • Silence Timeout: set the timeout before a call is automatically ended due to inactivity and the action (hangup or transfer) that should be performed when the call ends.
    In case you choose to transfer the call after the voice agent reaches the silence timeout, you need to specify:

    • Context: the Dialplan procedure

    • Extension: extension to which the call should be transferred
      
      

• Maximum Duration: the maximum duration of a call in seconds and action (hangup or transfer) that should be performed when the call ends.
  
  

• Click Add to save your voice agent and proceed with the Dialplan configuration (step 2 below).

Types of Voice Agents

Generative AI

When configuring Generative AI as the integration type, you need to create a clear and precise prompt with instructions for AI agents, which directly impacts voice agent's performance and reliability. Prompt engineering is an iterative process, so based on user feedback, you can refine your prompts for even better voice agent efficiency.

You can divide your system prompts into the distinct sections, each focusing on a specific element of the AI agent's behavior. For example:

1. Identity: define who the AI agent is, outline its persona and role to set the context for interactions.

2. Style: establish guidelines for the agent's communication style, including tone, language, and formality.

3. Response Guidelines: specify preferences for the response format, including any limitations or requirements in terms of the response structure.

4. Task and Goals: indicate the objectives the agent should achieve and outline the steps it should follow.
   
   

Webhook

Specify the following fields, when configuring Webhook as the integration type:

1. Target: enter the URL that the Webhook will use to send POST requests with the event payload.

2. Secret: the secret ensures that only requests from Wildix system are accepted, preventing unauthorized access or potential security breaches. The secret key is included in the headers of each POST request sent by the Webhook. Your server should validate this key to ensure the request is legitimate before processing the event data

If you configure AWS SQS as integration type, you need to provide the following details to establish the connection with your AWS SQS queue:

• Target: enter the URL of your SQS queue. This is where the events are sent, for example, https://sqs.amazonaws.com/11111/wildix-events-queue

• Key: enter your AWS Access Key ID. It is used to sign the request that x-bees / Collaboration 7 sends to AWS SQS.

• Secret: enter your AWS Secret Access Key, which is paired with your AWS Key to sign the requests securely.
  
  

Dialogflow CX

If you configure Dialogflow CX as the integration type, you need to fill out the following fields to establish the connection between x-bees / Collaboration 7 and your Dialogflow CX agent:

• Private Key: click Upload and upload the private key file associated with your Google Cloud service account

• Location: fill out the region where your Dialogflow CX agent is deployed (typically it is a region-specific identifier, for example, europe-west1, us-central1)

• Language: indicate the language that your Dialogflow CX agent will use to understand and respond to user inputs. Make sure the language code matches the languages supported by your Dialogflow CX agent, e.g.:en for English

• Agent ID: provide the unique identifier of your Dialogflow CX agent, links your voice agent to the specific Dialogflow CX agent that you’ve configured in Google Cloud.
  
  

OpenAI Assistant

If you configure OpenAI Assistant as integration type, you need to fill out the following fields to enable the connection between x-bees / Collaboration 7 and OpenAI's API:

1. API Key: enter the unique identifier that allows to grant access to the OpenAI API, which lets to send requests and receive responses from the Assistant

2. Assistant ID: fill out the unique identifier of a specific OpenAI Assistant you created.
   
   

Step 2. Configure Dialplan

To add voice agent to a Dialplan, use the Voice Bot application. Before adding the voice agent, make sure to set alaw/ ulaw codecs, as voice agent cannot be started in case the call was answered with opus codec: 

• Set -> Codecs -> alaw, ulaw

Also, set a language:

• Set -> Language -> select the language

Note:

• The following languages are supported:

  • English (British), English (US), French, Italian

  • Spanish, Dutch, German, Arabic, Catalan, Danish, Swedish, Portuguese - starting from WMS 6.09.20241106.2

  • Swiss German - starting from WMS 6.09.20241211.2

• Arabic (ar), Swedish (se) are not present in the drop-down list, but you can enter them manually, for example:
  
  

• Basque and Estonian languages are not supported

Add the voice agent:

• Voice Bot application -> choose the necessary voice agent

Choose speaker

You can change the default speaker by adding the following applications before the Voice Bot application in the Dialplan:

1. Set application -> choose the parameter Language - > choose language

2. Set application -> choose the parameter TTS Voice - > select speaker: 
   
   

Manage Voice Agents

The voice agents that you have created are displayed in WMS -> PBX -> Integrations -> Cloud integrations -> Voice Bots section. You can see the voice agent name, ID, and Integration type.

Edit a Voice Agent

1. To edit a voice agent, click on the Edit (pencil) icon:
   

2. Make the necessary changes and click Save:

Delete a Voice Agent

1. To delete a voice agent, click on the Delete icon:
   
   

2. On the screen that pops up, type the word “delete” and click Delete:
   
   

Traces

In Traces section you can see a table with the following information: session ID, voice agent name, caller, duration of the call, date and language:

Clicking on a session in Traces, you can view events of the session:

Voice Agents API

You can find voice agents API here.

Use Case: Using Voice and Chat Agents

You can enhance your experience of using Voice Agent feature by combining it with Chat Agent (you can find Chat Agent documentation here). For example, you can set up voice agent that would gather information from a customer and send it to the conversation with managers via a chat agent:

Step 1. Create a Chat Agent

1. Go to WMS -> PBX -> Integrations -> Cloud integrations

2. Select Chat Bots and click Add new Chatbot

3. Enter a name for your chat agent

4. Select the Webhook integration type for processing chat events

5. Fill out the Target field

6. Enable Allow users to find the chat agent using search checkbox to let users interact with it

7. Click Add to save and activate your chat agent 

After creating the chat agent, click on Manage API keys to create API key:

1. Click Create new API Key

2. Enter a name for identification

3. Click Create and copy the secret using the Click to reveal button. You will need the secret when configuring voice agent.
   
   

Step 2. Create a conversation

Create a conversation in x-bees / Collaboration 7 where you need to add the chat agent you’ve created as well as the managers who should receive the notifications.

Also, make sure to copy conversation ID, which will be required during voice agent creation:

Step 3. Create Voice Agent

Configure voice agent of Generative AI integration type.

In our example, we’ve used the following text as the First Message:
Hello! Do you have any complaints or suggestions regarding Wildix products?

And added the following instructions:

You are a customer care agent that collects all the complaints and suggestions about Wildix products. Try to understand with which product customer is having problems or has a suggestion. Carefully collect all the details. Then pass them to the manager in the chat.
Share with the manager any emotions or sentiments the customer had if any. Ask the customer their name before passing the information to the manager and remember to pass the customer's name as well. Hang up after saying thank you and good-bye if the customer says they have nothing else to add.

In Tools section, add Hangup and Third-party Function options:

We’ve used the following parameters in the Parameters section of Third-party Function section:

{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The message to the manager containing all the details about complains and suggestions collected from a customer"
}
},
"required": [
"text"
]

In Integration section, in the URL field (1) next to the POST Method, entered the following data:

https://api.x-bees.com/v2/conversations/channels/{Conversation_ID}/messages

Where {Conversation_ID} is the ID of the conversation from Step 2.

Click Add authorization and enter the Secret from Step 1 into the Bearer field (2):

Click Save to save the changes.

Step 4. Configure Dialplan

Set up voice agent in the Dialplan:

When calling the number set in the Dialplan, the call is answered by voice agent, which gathers the required information and send it to the conversation: