> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fetchlake.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Projects and import

> Set up a review project and bring in your search results.

## Create a project

From the Huxley home page, create a new project for each review. The project overview shows how many records you have and how many are included, excluded, maybe or still pending.

## Import records

Huxley imports **RIS** files, which nearly every database and reference manager can produce.

**1. Export from your database**

In Scopus, Web of Science, PubMed (via a reference manager), EBSCO, Ovid and so on, export your results as **RIS**. Include abstracts. Huxley screens on title and abstract.

**2. Upload**

In your project, choose **Upload a file** or drag and drop the `.ris` file.

**3. Check the count**

Make sure the number of records imported matches what the database reported.

## Tips

* **Remove duplicates first.** If you searched several databases, deduplicate in your reference manager (Zotero, EndNote and others can do this) before exporting one combined RIS file.
* **Keep the original export files** and note the search date and counts. You'll need them for your PRISMA flow diagram.
* Records with no abstract are hard for both you and the AI to judge. Expect more **Maybe** decisions for them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.