> For the complete documentation index, see [llms.txt](https://velodata.gitbook.io/velo-data/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://velodata.gitbook.io/velo-data/veloai.md).
# VeloAI
**VeloAI is currently in beta!**
Example Prompts
* What are the top performing coins this week?
* Which coins have a negative funding rate and a positive return today?
* Show me BTC open interest YTD.
* Show me ARB and OP price.
* Which coins have the most long liquidations this month?
* Which coins are up the most since BTC's low today?
* What are ETH IVs right now?
* Which coins have a market cap over $5B?
Reporting Mistakes
Should you suspect the AI has incorrectly interpreted one of your questions, you can help us improve the model by sending `!help [question]`.
Disclaimers
* Currently only UTC time is supported.
* The model has no memory between messages, meaning you need to type full queries each time.
---
# 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:
```
GET https://velodata.gitbook.io/velo-data/veloai.md?ask=
```
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.