> For the complete documentation index, see [llms.txt](https://docs.presearch.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.presearch.io/pregpt/faq/general-usage.md).

# General usage

## What can I ask PreGPT 2.0?

Feel free to ask PreGPT 2.0 anything - it's designed to handle a wide range of queries.

## What are the user eligibility requirements?

Anyone who registers on Presearch.com and subscribes and pays can access PreGPT 2.0.

## Can PreGPT store my chats for reference later ?

To prioritize user privacy, we've currently disabled the storage of all chats. However, in our upcoming tier release, the option for chat storage will become available.

## What languages are Supported ?

Current LLMs are able to answer in major world's languages.

## What are the chat input and output limits ?

You can input up to approximately 5,000 words in a single chat. The output length is approximately 650 words.

## Can PreGPT analyze Excel tables ?

Yes, you can input Excel tables for analysis and summarization.  Also ask Chattie to provide you copy/pasteable version responses for Excel or Gsheets.

## Can PreGPT do image analysis ?

Image analysis is on our roadmap but not yet available.

## Can I customize PreGPT 2.0?

Yes, you can customize PreGPT's behavior and tone to some extent by clicking the gear icon when starting a new chat. Where it says system prompt, type in a set of instructions or context that you'd like the AI to follow. Hit enter of simply wait and the system prompt will be guiding your chats going forward by default. This can include specifying a particular tone, such as formal, casual, or humorous, or directing the AI to adopt a certain role, like a tutor, advisor, or storyteller. This way, you can tailor the conversation to better suit your needs or preferences.

## What if I encounter any errors ?

If you run into any issues, try refreshing the page or initiating a new chat session. Occasionally, there will be network outages as well.


---

# 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.presearch.io/pregpt/faq/general-usage.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.