# Why WProofreader auto detect language doesn't work for small piece of texts?

By default, WProofreader uses the '**auto**' language, which automatically detects the language while a user typing. In order for the 'auto' algorism to identify the language of the text, there have to be at least **three existen words** or even more. If the language is not identified, there will be no highlightings.

For troubleshooting, check the proofreading language and type more text if it is 'auto'. If you still suppose that our proofreader doesn't process properly written text, report us via the [feedback form](https://forms.gle/31nm4p4Y5ARkf5JE9).

Note, the 'auto' language might be cached on your side and still be applied even if you specify a new default language on the client-side (product's configuration). So, after making changes, please clean your browser's local storage. To check the language in use you can in the network tab regarding the specific request.

<br>

<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.wproofreader.com/v6.10.0.0/faq/technical/languages/why-wproofreader-auto-detect-language-doesnt-work-for-small-piece-of-texts.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.