# 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.

<figure><img src="/files/090SfacG9EP5dWarRcwV" alt=""><figcaption></figcaption></figure>

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.

<figure><img src="/files/zVI2xGiAX5EPtVwBGhwi" alt=""><figcaption></figcaption></figure>

### Case 2 - Formatting responses for each channel

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

<figure><img src="/files/7qygSgO9yXT6EX4x8UK4" alt=""><figcaption></figcaption></figure>

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.

<figure><img src="/files/CtYifYJafMf2wp4n9OFM" alt=""><figcaption></figcaption></figure>

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.

<figure><img src="/files/mG7TwNsQgUTtHkEI68uH" alt=""><figcaption></figcaption></figure>

### 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.

<figure><img src="/files/2NxJnwFDoD5lkJWJXHF5" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.conversational-ai.syntphony.com/user-guide/ai-agents/how-to....md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.