> 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/deep-reseach/how-to-use-deep-research.md).

# How to Use Deep Research

Start by opening Deep Research from the composer and asking your question in plain language. You can also tap one of the quick start categories like Market or Investment if you want a head start.

<figure><img src="/files/wUTXGVrGZiBf9BRkmu8g" alt=""><figcaption></figcaption></figure>

Then choose your mode. Standard is selected by default and works well for most questions. Choose Depth if you want a more thorough report with more sources, or Ultra Depth if you want the most exhaustive research available.

<figure><img src="/files/x3q7YV0Mqe0hOpSdiILE" alt=""><figcaption></figcaption></figure>

Once you send your question, Computer gets to work searching, reading, and writing. Larger modes like Depth and Ultra Depth take longer since they cover more ground, so give it a few minutes to finish.

When the report is ready, it appears as a report card titled with your topic. Open the preview to read the full report in app, including an executive summary, detailed findings with citations, and a sources list. When you are happy with it, tap download to save it as a Word document you can share or edit further.


---

# 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/deep-reseach/how-to-use-deep-research.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.