> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/review-workflow/screening.md). # Screening Learn about the modes and AI tools available in Screening. **Screening** is where you decide which records from your search belong in your review. Every record added during Search moves into Screening and only the studies that meet your review's eligibility criteria remain. It creates an auditable inclusion or exclusion decision before you tag/extract included studies, and analyze your evidence. Before screening your first record, choose your reviewer structure, pass structure, and decision paradigm. Those choices determine how your team screens and records decisions. ### Tools Available Below is a summary of the Screening AI tools offered and what they do. | Tool | Paradigm | Role | Reads | | ------------------------------------------------------------------------------------------------------------ | ------------------------------ | ------------------------------------------------------------------------------------- | --------------------------------- | | [**Smart Config: Screening**](/review-workflow/screening/criteria-based-screening/smart-config-screening.md) | Criteria-Based Screening only | Builds criteria — drafts Abstract and Full Text Yes/No questions | Your research question | | [**Smart Screener**](/review-workflow/screening/criteria-based-screening/smart-screener.md) | Criteria-Based Screening only | Screens — answers every criterion Yes/No, for Abstract or Full Text | Abstracts or Full Texts | | [**Screening Model**](/review-workflow/screening/exclusion-based-screening/screening-model.md) | Exclusion-Based Screening only | Prioritizes — assigns an inclusion probability to sort the queue; doesn't decide | Your team's adjudicated decisions | | [**Robot Screener**](/review-workflow/screening/exclusion-based-screening/robot-screener.md) | Exclusion-Based Screening only | Screens — fills one reviewer seat in Dual Screening (Abstract stage only in Two Pass) | Your team's adjudicated decisions | ### Choose Your Screening Setup

Decision tree for selecting a reviewer structure and pass structure: Single or Dual Screening, and Standard or Two Pass Screening. — Choose a reviewer structure and pass structure before configuring Screening.

### Configure Screening Choose a reviewer structure, pass structure, and screening paradigm in **Configure Screening**. Single Screening uses one reviewer. Dual Screening uses two reviewers and human adjudication for disagreements. Standard Screening uses one screening round. Two Pass Screening separates abstract and full text screening.


Configure Screening	Choose reviewer structure, pass structure, and screening paradigm.	Configure Screening

### Option 1: Screen With Eligibility Criteria Use **Criteria-Based Screening** when your protocol uses Yes/No eligibility questions. A record advances when every criterion is answered Yes. Any No excludes it. Use **Smart Config** to draft criteria from a research question. Use **Smart Screener** to answer configured criteria. Review the setup before screening begins.


Criteria-Based Screening	Set up Yes/No eligibility questions for each record.	Criteria-Based Screening

### Option 2: Screen With Exclusion Reasons Use **Exclusion-Based Screening** when you need an exclusion reason for each excluded record. This setup supports PRISMA exclusion counts by reason. Use the **Screening Model** to prioritize records in Single Screening. In Dual Screening, **Robot Screener** can fill one reviewer seat. A human reviewer and human adjudicator remain required.


Exclusion-Based Screening	Assign an exclusion reason to excluded records.	Exclusion-Based Screening

Screening workflow showing records moving through configuration, screening decisions, and review. — Screen records using eligibility criteria or exclusion reasons.

#### Import Screening Decisions Use **Import Screening Decisions** when your team screened records in another tool. Imported decisions use the **Exclusion Reasons** paradigm.


Import Screening Decisions	Add screening decisions from another tool.	Import Screening Decisions

### Screen And Review Records After configuration, screen records in a queue against your criteria or exclusion reasons. In **Dual Screening**, resolve reviewer disagreements through adjudication. Use **Study Inspector** filters to find records by screening decision.


Screen Records	Make decisions against configured criteria or exclusion reasons.	Screen Records
Adjudicate Records	Resolve disagreements in Dual Screening.	Adjudicate Records

### Apply Tags in Screening You can also apply tags during Screening.


Apply Tags In Screening	Apply tags while you review records.	Configure Screening

### What Happens After You Screen Records Each record is assigned a screening decision that you can filter to, view, edit and download later. All included records move into the Tagging queue for data extraction. The PRISMA diagram is auto-generated for you


Filter Records In Study Inspector	Filter records by their screening decision.	Study Inspector
PRISMA In Synthesis	View and download your nest's PRISMA diagram.	PRISMA Chart

## Next Steps


Configure Screening	Choose reviewer structure, pass structure, and screening paradigm.	Configure Screening
Criteria-Based Screening	Set up Yes/No eligibility questions for each record.	Criteria-Based Screening
Exclusion-Based Screening	Assign an exclusion reason to excluded records.	Exclusion-Based Screening
Screen Records	Review records and make screening decisions.	Screen Records
Adjudicate Records	Resolve disagreements in Dual Screening.	Adjudicate Records
Full Text Import	Import PDFs before Full Text Screening.	Full Text Import

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.nested-knowledge.com/review-workflow/screening.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.