# Introducing AI QueryBot on Sketchnote!

In today's fast-paced world, information is king. But actually extracting vital pointers from the vast sea of information is a bit of an arduous task.

Our latest release is about to change this time-consuming process into a fun and quick assignment. Introducing Sketchnote's AI QueryBot, where we've harnessed the power of artificial intelligence to extract the most important bits of information from your detailed data, just when you need them.

Let's tell you all about it!

{% embed url="<https://www.youtube.com/watch?v=2gYF0n8jjH0>" %}

**AI QueryBot for all your queries**

Imagine if, like most prompts, you could simply ask AI to tell you what a PDF document was all about. You don't have to imagine it anymore. With Sketchnote's AI QueryBot, you can actually do this!

So whether it's a legal paper, or a new agreement, or even a government circular—all you need to do is upload it to the AI QueryBot view on Sketchnote.

<figure><img src="/files/LJ1UyoPDaV4wgI8MCm8r" alt=""><figcaption></figcaption></figure>

We've turned AI QueryBot into a file view. Why? So that you can save your PDF docs and the questions you've asked on it as a file. This means your colleagues too can open it at any time, see pre-asked questions and build on top of it!

<figure><img src="/files/G8a30Mbvc69b1nFpIWRr" alt=""><figcaption></figcaption></figure>

Psst: Make sure the PDF is a typed out document and not a handwritten one, for more accurate results!

This amazing new feature is available for free for all Sketchnote users for a limited period, and will be part of our AI credit package at a later date. So go on, give this new feature a spin!


---

# 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://changelog.sketchnote.co/introducing-ai-querybot-on-sketchnote.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.
