Search Docs…

Search Docs…

Tutorials

Tutorials

Tutorials

Custom Tools

Custom Tools

Custom Tools

Background

To understand how custom tools work, let’s take a peek under the hood of the Bland AI phone agent.

During the conversation, the phone agent is constantly listening to figure out when it’s supposed to respond. When the phone agent realizes it’s time to respond, it reviews the tools in its toolbox and picks between them.

Those tools include a speak, wait, and button press tool. When you create a custom tool, you add it to the existing ‘toolbox’ for the phone agent to pick from.

A few natural questions arise:

  1. How do I define my custom tool?

  2. How do I make sure my tool gets picked at the right time?

  3. How does information from the call get passed to my custom tool’s API request?

  4. How do I fill the silence (when my custom tool is running)?

  5. How does the response from my custom tool get added to the call?

Keep reading to find out.

Creating your custom tool
Custom Tool Example
{
    "name": "BookAppointment",
    "description": "Books an appointment for the customer",
    "url": "https://your-api.com/book-appointment",
    "method": "POST",
    "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
    },
    "body": {
        "date": "{{input.date}}",
        "time": "{{input.time}}",
        "service": "{{input.service}}"
    },
    "input_schema": {
        "example": {
            "speech": "Got it - one second while I book your appointment for tomorrow at 10 AM.",
            "date": "2024-04-20",
            "time": "10:00 AM",
            "service": "Haircut"
        },
        "type": "object",
        "properties": {
            "speech": "string",
            "date": "YYYY-MM-DD",
            "time": "HH:MM AM/PM",
            "service": "Haircut, Coloring, Trim, or Other"
        }
    },
    "response": {
        "succesfully_booked_slot": "$.success",
        "stylist_name": "$.stylist_name"
    }
}

From API request to custom tool

The next step is to convert the API request into a custom tool. Custom tools have the following properties:

  • name - the agent will see this in the list of tools

  • description - a short explanation of what the tool does

  • input_schema - a JSON schema describing the input data

  • speech (optional) - a string that will be spoken to the agent while your tool waits for a response

  • response_data - An array of objects that describe how to extract data from the response. Within the response data, you can create variables that the phone agent can reference in its prompt.

Name & Description

The agent will see the name in the list of tools. The name, plus the description, help the AI phone agent when it decides which tool to use.

For this example we’ll set the name to BookAppointment and the description to Books an appointment for the customer.

Input Schema

The input schema is critical. It defines the shape of the API request, the different inputs the request can take, and also includes an example (which helps our system when creating requests).

Here’s what the input schema could look like:

    "input_schema": {
        "example": { // "example" is a special property that shows an example of what the input object the agent creates should look like
            "speech": "Got it - one second while I book your appointment for tomorrow at 10 AM.",
            "date": "2024-04-20",
            "time": "10:00 AM",
            "service": "Haircut"
        },
        "type": "object",
        "properties": {
            "speech": "string",
            "date": "YYYY-MM-DD",
            "time": "HH:MM AM/PM",
            "service": "Haircut, Coloring, Trim, or Other"
        }
    }

Two important notes about input schema:

  1. input_schema is converted into the variable "{{input}}" that you can use in the request body/query/headers

  2. To access nested properties, use dot notation: "{{input.property.subproperty}}"

    • For example, later on you could use "{{input.service}}" to have whatever type of appointment that the customer wants

What you’re doing here is describing the structure of the variables that the agent will create.

Special Note: If you need to gather detailed letter-by-letter information from the user, raise your interruption_threshold parameter to about 200 so that the AI doesn’t interject so quickly.

Scroll down to see the full example.