> For the complete documentation index, see [llms.txt](https://docs.feedloop.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.feedloop.ai/agent-settings/training/answering.md).

# Answering

{% hint style="info" %}
training answering is related to the card system.
{% endhint %}

Training Answering involves teaching the AI agent how to present retrieved data in a chat format. This process ensures that after retrieving the necessary information, the AI agent can effectively communicate it to the user in a clear and structured manner. The instructions include guidelines on how to format the response, what additional elements to include, and the sequence of presenting the information.

**Steps to Train the AI Agent for Answering:**

1. **Input Condition:** Define the conditions that must be met for the AI agent to use a particular skill to activate training
2. **Input Instruction:** Define how the AI agent should answer and display data during specific scenarios or interactions.
3. **Input Condition:** Define the conditions that must be met for the AI agent to use a particular skill to activate training

<figure><img src="https://4292326968-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FqsAGx1GJXq13bQhP2sY7%2Fuploads%2FJRxXQ8SvxhIMtiiidgmj%2Fimage.png?alt=media&amp;token=fe63a5b6-afc9-4e8a-97c2-12366997e9a0" alt="" width="286"><figcaption><p>Add training answering</p></figcaption></figure>