# Overview

Getting started with Cohesive's extraction workflows involves three concepts:

1. [**Templates**](/reference/workflow-documentation/templates.md)**:** these represent the expected output to be extracted from uploaded files. Cohesive supports a robust set of output fields, including mathematical or date-based expressions (e.g., adding 30 days to a date from a specific field in the document)
2. **Extraction:** this represents the action of taking one or more uploaded files, and running extractions based on the chosen template. The status of extractions will be shown on the `jobs` page
3. **Export:** this represents the action of exporting the data out of Cohesive, such as exporting to a `CSV` or syncing to `Netsuite` or `Google Sheets`. Exports can be triggered on the `jobs` page, and you have the option of adjusting the data before completing the export.

## Getting started: example workflow (export to CSV)

### Step 1: uploading the files

To upload files (you can upload in bulk), navigate to the `Files` page, and press `Upload files`. Choose the files you wish to upload, and press `Upload`. Once the files are successfully uploaded, you will see them on the table

<figure><img src="/files/qb0j733iE8vUCjAmpP3z" alt=""><figcaption></figcaption></figure>

### Step 2: running a bulk extraction

*Note that this assumes that you've already set up a template. See the* [*templates*](/reference/workflow-documentation/templates.md) *page for more information about setting up a template.*

Select the files you wish to extract at once (using the checkboxes on the left-most column of the table), and press `Bulk extract`. Enter a name for the bulk extraction job, and choose a `template` to use for the bulk extraction.

The results of the bulk extraction will show up on the `jobs` page as a row in the table.

<figure><img src="/files/wDSn1RilkocbFR97e4es" alt=""><figcaption></figcaption></figure>

### Step 3: export to CSV

In the `jobs` table, press the `Export` button on the rightmost column of the table. You can check the extracted data by pressing `edit` for a specific file, and adjust as necessary on the right table.&#x20;

Once done adjusting, press `Export to CSV`, and the CSV export should be automatically downloaded. That's it :tada:

<figure><img src="/files/YbdvQCeQwt1yFcXj2rbB" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
By default, if a template has a `List` field, then each entry within the `List` field will result in a new row in the CSV export, with the other fields being repeated for each row.&#x20;

To prevent this, manually clear out the value (in the rightmost table) for the `List` field for the first file. For example in the image above, if `accountNumber` was hypothetically a `List` field and we DIDN'T want a separate row for each entry, then delete the 607B5E0 value.
{% endhint %}


---

# 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://docs.cohesiveapp.com/reference/workflow-documentation/overview.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.