> For the complete documentation index, see [llms.txt](https://docs.1millionbot.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.1millionbot.com/chatbot/knowledge-base/training/validation-and-training-of-the-assistant.md).

# Validation and training of the assistant

In the training section we can review user interactions with the assistant and use them to improve its operation.

When opening the section, the list of messages that the assistant has received that have not yet been reviewed is displayed, ordered from the most recent to the oldest.

There are two functions in this section:

* **Message review:** In the verify icon we can mark that message as reviewed to later filter by the messages that have already been verified from those that have not.
* **Add message or messages to an intent:** Each message is associated with a specific intention by artificial intelligence. If you detect that this message should belong to another intention, you must click on the dropdown and select the corresponding intention in the pop-up window. This allows the assistant to be trained and thus offers more and more correct answers.

To add one or more messages to an intent, you must click on the dropdown. Within this window appear the messages that are going to be added to the intention. Clicking on the intent brings up a complete list of all the intents already created. The finder of this selector can be used both to find an intent and to create a new one. At the bottom of the window, the revision of the same is always selected by default once it has been added to another intention. If you do not want this to happen, you can deactivate this option.

There are different ways to filter the list of messages, by date of receipt, by revision or by grouping.

It is possible to filter by the following groups:&#x20;

* **Conversations**: With this grouping you can see the complete list of messages received by a user given a few dates.
* **Intents**: With this filter you can group the messages that belong to a specific intent or to the entire list of intents.

Once the grouping filter is activated, you can expand the results to see the messages that are within each conversation or intent. If you want to display all the hit results, you can click on the 'Unfold all' button.

There is also the 'Select all' function which allows you to select all the messages that appear in the list and perform the actions of 'Add to intent' or 'Review', (which is found within the contextual menu) on them.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.1millionbot.com/chatbot/knowledge-base/training/validation-and-training-of-the-assistant.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
