# Best practices

Here are some good practices on creating and using intents.

1. Insert a similar number of training phrases into all intentions. In this way you will ensure that it works correctly and that the Artificial Intelligence selects the appropriate intention.
2. To increase detection accuracy, you need to add a minimum of 10 training phrases to each intent. Our recommendation is that if possible, add around 30.
3. Make sure that the training phrases are unique to each intention. Having intents with very similar user phrases can cause AI to miss the correct intent.
4. Use a wide vocabulary. A common mistake when creating intents is to prioritize the quantity of user phrase examples over the quality of the intents. To ensure that the assistant can detect the various ways in which the end user may request the same thing it is important to ensure that the user phrases cover a wide range of vocabulary and wording.
5. Avoid incomplete sentences or sentence fragments.
6. Use simple language, using expressions that end users could make.
7. Add phrases that mean the same thing but are structured differently, using synonyms, different tenses, etc.
8. Use the same type of entity in several sentences of an intention, being recommended at least 3 times.
9. Use inclusive language, which allows you to include a diverse group of end users.<br>


---

# 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.1millionbot.com/chatbot/knowledge-base/intents/best-practices.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.