# AI-based language doesn't provide suggestions for non-existent words

AI-based English was trained to work with **real** text and skip non-existent wording, that is usually random combinations of letters typing like words in haste for testing purposes. The AI-based engine ignores such nonsense wording and doesn't provide any suggestions for them even if they are in the middle of the real text. But it works if you try to make a misspelling in a real word.

The default language for our products is 'auto', that applies AI-based proofreading for text once the English language is identify. This means that 'auto' language will not provide suggestions for non-existent words as it will use the AI-based engine under the hood for English texts.

Unlike AI-based engines, the classic spell checking is very “simple” (e.g. American English), it relies on the wordlist. And if the word is not in the dictionary, it will be considered a misspelt word. In that case, such a word would be underlined since the spell check mechanism is built on top of the wordlists. Thus, when you switch to a dictionary-based language, you can see the suggestions for non-existent words.


---

# 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/v6.12.0/faq/technical/languages/ai-based-language-doesnt-provide-suggestions-for-non-existent-words.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.