Variables

​

Understanding Variables in NLPearl.AI

When creating a Pearl in NLPearl.AI, one of the most powerful tools at your disposal is the use of variables. These variables allow you to dynamically personalize conversations, making them more engaging and contextually relevant. Understanding how to use these variables effectively is key to getting the most out of your AI-driven interactions.

​

Built-In and Custom Variables

NLPearl.AI comes with a set of built-in variables such as firstName, lastName, agentName, companyName, etc. However, you also have the flexibility to create custom variables to suit your specific needs.

​

Creating a Custom Variable

When creating a new variable, you need to provide the following details:

• Display Name: This is how the variable will appear on the platform and in the call information. It’s the human-readable name of your variable.
• Id: This is the unique identifier for the variable, which you will use as a key in callData in Make Call API Request. The Id is automatically generated when you fill in the Display Name but can be customized.
• Type: The data type of the variable, such as boolean, float, int, or string.
• Description: This is a critical field where you describe the purpose of the variable. It’s important to fill this out wisely, especially if the variable is meant to be collected during the call.

​

Types of Variables

There are two main types of variables:

​

1. Predefined Information Variables:

These variables hold information that is known before the call and can be used as placeholders in your conversational flow.

​

Example Usage:

• Opening Sentence: “Hello, I am agentName from companyName. How can I assist you?”
• Script Example: “Ask the prospect if his name is still firstName lastName.”

You can also create your own variables to be used in a similar fashion. For instance, if you are selling cars, you could create variables like Brand, color, or priceProposed.

see Make Call API Request.

​

API Request Example:

{
  "to": "+1345678991",
  "callData": {
    "firstName": "Josh",
    "lastName": "Martin",
    "brand": "BMW",
    "color": "gray",
    "priceProposed": "two hundred thousand dollars"
  }
}

• Opening Sentence: “Hello firstName, I am calling about the color brand you were interested in…”
• Script Example: “Ask the prospect if he agrees with the price priceProposed.”

Important: Make sure to use the Id (e.g., priceProposed) of the variable in your API request dictionary, not the Display Name (e.g., Price Proposed), to ensure proper functionality.

​

2. Collected Information Variables:

These variables are used to gather information during the call that was not known beforehand. For example, you might instruct Pearl to ask the prospect what price they are willing to pay: “Ask the prospect what the priceProposed they want.”

Once the information is collected, it can be reused in the conversation and utilized in any actions requiring this variable. At the end of the call, it will be displayed in the “Call Information” section of the call details.

​

Mixing Use Cases

You can combine the use of predefined and collected information variables in a single script. For example:

• Script Example: “Verify the price priceProposed with the prospect.”

If you already have this information before the call:

{
  "to": "+1345678991",
  "callData": {
    "firstName": "Josh",
    "priceProposed": "two hundred thousand dollars"
  }
}

Here ,Pearl will simply ask for confirmation of the price.

-If you don’t have the information:

{
  "to": "+1345678991",
  "callData": {
    "firstName": "Josh"
  }
}

Pearl will ask for the price during the call based on the variable’s definition.

​

Conclusion

Variables in NLPearl.AI offer a powerful way to personalize and optimize your AI-driven conversations. By effectively defining and utilizing variables—whether for integrating pre-existing information or collecting new data during calls—you can significantly enhance your Pearl’s performance and the overall customer experience. Additionally, variables can be leveraged in actions such as sending SMS, emails, or other post-call activities, enabling tailored communications based on the insights gathered during interactions.