> ## 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.

# Huxley

> Title and abstract screening for systematic reviews, with an AI that screens alongside you.

Huxley helps you get through the screening stage of a systematic or scoping review. You import search results, write down your inclusion and exclusion criteria, screen with keyboard shortcuts, and let **Huxley AI** take a first pass at the rest. Then you check its decisions and export what you've included.

Huxley uses your Fetchlake account. Open it from **Dashboard → Systematic Review**, or choose **Continue with Fetchlake** on the Huxley sign-in page.

## The workflow

**1. Import your search results**

Create a project and upload the RIS file from your database search. [Projects and import →](https://docs.fetchlake.com/huxley/projects-and-import.md)

**2. Write your criteria**

Set what must be included or excluded, using keywords or Boolean rules. [Criteria →](https://docs.fetchlake.com/huxley/criteria.md)

**3. Screen**

Make include, exclude or maybe decisions one article at a time. [Screening →](https://docs.fetchlake.com/huxley/screening.md)

**4. Run Huxley AI**

Let the AI screen the remaining records against your criteria, with a reason and confidence for each. [AI screening →](https://docs.fetchlake.com/huxley/ai-screening.md)

**5. Review and export**

Check AI decisions, override where you disagree, and export the result as RIS. [Review and export →](https://docs.fetchlake.com/huxley/review-and-export.md)

## Decision types

| Decision | Meaning |
| - | - |
| ✓ **Include** | Meets your criteria. Goes forward to full-text review. |
| ✗ **Exclude** | Doesn't meet your criteria. |
| ? **Maybe** | Can't tell from the title and abstract. Check the full text. |
| ○ **Pending** | Not screened yet. |

Every decision records who made it: **manual** (you) or **Huxley** (the AI), so you can always filter to check the AI's work.

## Using Huxley well

> [accordion] Screen a sample yourself first
>
> Screen 50–100 records by hand before running the AI. It shows you whether your criteria are clear, and gives you something to check the AI's decisions against.

> [accordion] Write criteria the AI can apply
>
> Be specific: "randomised controlled trials in adults aged 18+" works better than "good quality studies". The AI only sees the title and abstract, so criteria that need the full text belong at the next stage.

> [accordion] Treat the AI as a second screener, not the only one
>
> Review every AI exclusion with low confidence, and spot-check a sample of the confident ones. Report in your methods that AI-assisted screening was used and how it was checked.

> [accordion] Lean towards Maybe
>
> Turn on **Maybe** decisions for the AI. Sending a borderline paper to full-text review costs a few minutes. Wrongly excluding a relevant paper weakens the review.


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