> For the complete documentation index, see [llms.txt](https://help.imagine.art/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.imagine.art/imagine-computer/ai-tools/build-graphs/how-to-use-ai-graphs.md).

# How to use AI Graphs

Start by connecting a data source or asking directly. Use Add Data Source to link Google Sheets, Google Drive, Notion, a CSV or Excel file, or an ad platform like Google Ads or Meta Ads, or use Import URL to pull data straight from a link. You can also just type your request and Computer will ask for a source if it needs one.

Prefer a head start? Choose from ready made templates like **Customer Support Analytics,** **E-commerce Store Analytics**, **Financial P\&L Overview**, **Fitness & Health Tracker** etc. Each one shows a live preview, and you can open it directly to start from a working dashboard.

<figure><img src="/files/MiAPs4ml18Ur7FrHBfHc" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/qdcMozC9bof56OSBNuda" alt=""><figcaption></figcaption></figure>

Then just ask for what you want. Describe the chart or dashboard in plain language, for example "Show me the top 10 products by sales" or "Compare Meta Ads spend vs conversions from Supermetrics."

Computer will pick a sensible chart automatically, such as a line, bar, or donut chart, and can build a full dashboard with several charts and key metrics like total tickets, average resolution time, or top category share.

You can refine it right in chat. Ask to rename a chart, change its chart type or colours, filter it further, or focus on a specific metric, and Computer updates just that part without touching the rest.


---

# 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://help.imagine.art/imagine-computer/ai-tools/build-graphs/how-to-use-ai-graphs.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.