How to...

This section presents common use cases that show how to configure Actions and Skills to meet practical needs. Each example covers typical scenarios when designing AI Agents. It explains how to structure data collection, manage execution flow, and adapt behavior to different contexts using the platform’s documented capabilities.

Case 1: Confirm data to call a service

There is a transactional API that requires specific user data to be confirmed before it runs. Once confirmed, an OTP code is generated and the API is invoked.

To meet this requirement, create an Action to collect the required data and trigger the OTP code generation service. Then, create a second Action to perform the transactional query.

Case 2 - Formatting responses for each channel

To meet this requirement, create an Action with a simple prompt to format responses.

Next, each property was defined with a channel-specific formatting prompt (for example, web chat, WhatsApp, or voice). This allows the AI Agent to generate the appropriate output for each target channel.

Finally, a response was created in which the corresponding variable was used for each channel. This ensures that the format and content are correctly adapted to each channel type.

Case 3 - Triggering an Action after a skill

Sometimes an Action needs information that it doesn't have yet. In these situations, you can instruct an Action to work with other Actions or skills before completing its task.

In the example below, the create_ticket Action first uses another capability to validate and gather the required information. Once everything is confirmed, it proceeds with ticket creation.

This approach helps ensure that Actions always have the context they need before executing a task.