How to...

This section presents common use cases that illustrate how actions and skills can be configured to address practical requirements. Each example demonstrates typical scenarios you may encounter when designing agents, helping you understand how to structure data collection, control execution flow, and adapt behavior to different contexts using the documented capabilities of the platfo

Case 1: Confirm data to call a service

I have a transactional API that, in order to run, requires certain user data to be confirmed in order to generate an OTP code and then invoke the API.

To address this need, it is necessary to create an Action designed to collect the data required to invoke the OTP code generation service, and subsequently, a second action responsible for performing the transactional query.

Case 2 - Formatting responses for each channel

To address this requirement, create an action with a simple prompt whose purpose is to format responses.

Subsequently, each parameter was defined with its own channel-specific formatting prompt (for example, web chat, WhatsApp, or voice), allowing the agent to generate the appropriate output depending on the target channel.

Finally, we created a response in which, for each channel, we used the corresponding variable, thus ensuring that the format and content were correctly adapted to each type of channel.

Case 3 - Triggering an Action After a Skill

Here we indicate in the prompt how this Action should interact with the others to complete its knowledge.