> For the complete documentation index, see [llms.txt](https://docs-en.dydu.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-en.dydu.ai/preferences/bot/automated-interaction-categorization.md).
# Automated Interaction Categorization
## How it Works
Automated categorization allows you to intelligently sort and organize your bot's exchanges. At the end of each conversation, the LLM analyzes the interaction content and automatically classifies it according to defined categories.
**Operating Principle**
This system is based on a fully customizable configuration:
* **Custom Creation :** You define and create the different categories into which interactions should be classified.
* **Description as Instructions (Prompt) :** When creating a category, the "Description" field plays a fundamental role. The text you write there serves as a direct instruction (prompt) for the LLM. It is through this description that the LLM understands the attribution criteria and knows how to classify interactions. Each description is limited to 500 characters.
* **Continuous Analysis :** The model analyzes each newly completed conversation and places the interactions into the corresponding category based strictly on your descriptions.
## Implementation
To start using automated categorization, you must first enable it by clicking the dedicated activation button.
Once the feature is enabled, you have two methods for creating your categories:
* **Individual Addition :** Simply enter the category name in the corresponding field, then click Add. Once the category is added to your list, click on the empty description area to write or edit the instructions (the prompt) for the model.
* **Bulk Addition :** To save time and import several categories simultaneously, click the Bulk Add button. A window will open. Simply list your various categories there, strictly following this template (using a new line for each entry):
> `: `
---
# 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-en.dydu.ai/preferences/bot/automated-interaction-categorization.md?ask=&goal=
```
`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.