Skip to main content
Mid-call tools allow your AI assistant to interact with external systems during calls. Whether checking inventory, verifying customer data, or retrieving real-time information – these tools make your AI more powerful and connected.

Overview

Tools during the call enable your AI assistant to:
  • Make real-time API calls during conversations
  • Retrieve or submit data from/to your systems
  • Make informed decisions based on live data
  • Provide accurate, up-to-date information to callers

Key Benefits

  • No coding required – simply configure API endpoints and parameters
  • AI automatically knows when and how to use the tools
  • Real-time data access during calls
  • Seamless integration with your existing systems

Setting Up Your Tool

1. Basic Configuration

Main Tool Configuration

  1. Access tool creation Navigate to “Tools During the Call” and click “New Tool”
  2. Configure main settings Fill out the essential details:
    • Name: Use lowercase letters and underscores (e.g., check_order_status)
    • Description: Explain when and how the AI should use this tool
    • Endpoint: Your API URL (e.g., https://api.yourcompany.com/orders)
    • Timeout: How long to wait for responses (in seconds)
    • Method: Choose GET, POST, PUT, PATCH, or DELETE
  3. Add headers Common headers you might need:

2. Variable Configuration

Defining Parameters

  1. Define parameters These are the pieces of information your AI will collect during the call:
  2. Set validation rules Add format requirements in the description:

Understanding Parameter Types

String

Text values like names, addresses, or reference numbers

Number

Numerical values like amounts, quantities, or IDs

true_false

Boolean values for yes/no situations

Formatting guidance

Include formatting instructions in descriptions:

Dynamic Endpoints

If you use variables in your endpoint URL, make sure to enclose them in curly braces and use the exact parameter names. You can create dynamic endpoints with variables:
The AI will automatically replace {order_id} with the actual value collected during the conversation.

Simple Testing

Automated Testing

Click “Test Tool” to run a test with dummy data:
  • String parameters: “test”
  • Number parameters: 1
  • Boolean parameters: true
You will see the response code and body to verify that everything is working.

Power User Feature: Automation Platform Integration

Need more complex logic? Connect your tool to the Famulor automation platform for advanced workflows. How to build powerful integrations: In the automation platform:
  1. Create a new flow
  2. Add a webhook trigger
  3. Build your logic (API calls, data transformations, etc.)
  4. Finish with “Return Response”
In your tool during the call:
  1. Use the webhook URL as your endpoint
  2. Append /sync at the end
  3. Example: https://automation.famulor.de/webhook/abc123/sync
This allows you to:
  • Transform data before/after API calls
  • Chain multiple API calls sequentially
  • Implement complex business logic
  • Handle errors gracefully

Practical Examples

Order Lookup System

The AI will:
  • Ask for the order number
  • Retrieve the status
  • Explain delivery dates and status to the customer

Appointment Availability

The AI will:
  • Ask for the desired service
  • Inquire about the preferred date
  • Show available time slots

Customer Verification

The AI will:
  • Collect contact information
  • Verify it against your CRM
  • Proceed based on verification status

Configuring Your AI

The AI requires clear instructions in its system prompt to effectively use your tools during the call. Example prompt section:
Test your tools with various conversation flows to ensure the AI handles all scenarios smoothly. Start with simple test calls before going live.

Further Resources

Understanding Mid-call Actions

Learn more about the technical basics and how they work

Use Cases

Discover when mid-call actions provide the most value

Integration Templates

Use prebuilt templates for popular systems

Note: Tools during the call can be combined with other Famulor features. For example, the AI can check an order and then, if further support is needed, escalate to a human agent.
Need a whole toolset instead of building HTTP actions one by one? Connect an external MCP server — tools are discovered automatically. See MCP Servers.