> For the complete documentation index, see [llms.txt](https://help.csvbox.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.csvbox.io/dashboard-settings/ai-bulk-transforms.md).

# AI Bulk Transforms

{% hint style="info" %}
Currently in Beta
{% endhint %}

### How to Enable AI Transformations

To enable this feature for a sheet:

1. Go to your **Sheet Settings**
2. Click on the **Import Steps** tab
3. Navigate to the **Verify Data** tab
4. Set **"Enable AI Transformations?"** to **Yes**
5. Save your settings

Once enabled, a new **"Bulk Transform"** option will appear in the Verify step of the import flow for each column.

<figure><img src="/files/PRHzM8kAhVigPdYfKb8E" alt=""><figcaption><p>Bulk Transform Button</p></figcaption></figure>

<figure><img src="/files/SO5oOuamTO4M8RGhde2R" alt=""><figcaption><p>AI Bulk Transform Screen</p></figcaption></figure>

### What Can It Do?

The users can use this tool to clean, format, and enrich the data effortlessly using plain language. It  can:

* Capitalize or lowercase text in `'product_name'`
* Add a 10% markup to values in `'price'`
* Translate `'description'` to Spanish
* Format `'order_date'` to `YYYY-MM-DD`
* Extract the domain name from `'email'`
* Tag rows as `'Yes'` in `'priority'` if `'notes'` mention "urgent"

These are just a few examples — the feature is flexible and can handle a wide range of transformations across different languages.

### Key Features

* Transform entire columns using simple AI prompts.
* User data never leaves the browser — values are *not* sent to any external AI models.
* Fix validation issues quickly by modifying problematic fields in bulk.
* Users can modify or delete rows, but cannot add new rows using AI.
* Supports prompts in all languages available in the importer.
* Users can preview the data before applying changes.


---

# 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.csvbox.io/dashboard-settings/ai-bulk-transforms.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.