> For the complete documentation index, see [llms.txt](https://docs.quadratichq.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.quadratichq.com/quadratic-ai/getting-started.md).

# Getting started

## Getting started

### AI Chat

Quadratic AI Chat is built to turbocharge your work. Every step of your analyses can be sped up and made more accessible, from generating code to generating new datasets entirely from scratch. Create, edit, and refine, all with Quadratic AI.

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><span data-gb-custom-inline data-tag="emoji" data-code="1f469-1f4bb">👩‍💻</span> Learn how to use Quadratic AI to generate code -></td><td></td><td></td><td></td></tr><tr><td><span data-gb-custom-inline data-tag="emoji" data-code="1f522">🔢</span> Learn how to use Quadratic AI to generate datasets -></td><td></td><td></td><td></td></tr></tbody></table>

{% @arcade/embed url="<https://app.arcade.software/share/WmxlS1QtUZ0acwCuIBVJ>" flowId="WmxlS1QtUZ0acwCuIBVJ" %}

#### Generate code from scratch and edit existing code

* Develop entire models and analyses from scratch
* Build infinitely flexible charts without writing a line of code
* Debug and fix errors in existing code and formulas

Learn how to generate code using Quadratic AI ->

#### Generate datasets

* Create new datasets from scratch
* Augment and edit existing data
* Smart insert and relocate data via chat

Learn how to generate datasets using Quadratic AI ->

### Reference your data with @-mentions

Type `@` in the chat to reference sheets, tables, cell ranges, or connections. Mentions become pills in your message and give the AI full context on whatever you referenced — including your live database connections.

### Attach files

Attach PDFs, images, Excel, CSV, or Parquet files to the chat with the paperclip, by pasting, or by dragging them in. Spreadsheet files import directly; PDFs and images are read by the AI so you can extract exactly what you need. Learn more in Import PDFs and Import images.

### The AI asks before it guesses

When your request is ambiguous, Quadratic AI asks a clarifying multiple-choice question in the chat instead of guessing. Answer with a click — or pick "Other" and type your own answer — and it continues from there.

### Trace any value

Right-click a cell and choose **Trace value** to have the AI explain where a value comes from — the formula, code cell, table, or connection that produced it, and everything upstream of it.

### Pick your model

Choose the AI model that powers your chat from the model menu at the bottom of the chat panel. Claude Sonnet 5 is the default; additional models are available on paid plans. A context gauge next to the menu shows how much of the model's context window the current chat has used. Learn more in AI models.

### Memory

Quadratic AI remembers durable context at a personal, team, and connection level, so you don't repeat yourself between chats. Learn more in AI memory & context.

### Notifications

Working on something else while the AI runs? Quadratic can send a browser notification when a long-running response finishes while you're in another tab.


---

# 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.quadratichq.com/quadratic-ai/getting-started.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.