AI as the Only Reviewer in EasySLR

AI as the Only Reviewer in EasySLR

What is “AI as the Only Reviewer”?

The AI as the Only Reviewer feature in EasySLR allows the AI to independently perform screening — making inclusion/exclusion decisions across your dataset without requiring input from a human reviewer.

How to Enable AI as the Only Reviewer
  1. Navigate to Project Settings.
  2. Under Workflow, select:
    • Set Number of Reviewers to 1.
    • Enable AI as Reviewer under the AI Copilot section.
  3. Make sure AI is enabled for the relevant stage (Title-Abstract or Full-Text).
  4. Save your settings. The AI will now screen all records on its own and assign decisions with rationale.
How It Works
  • AI screens each article by applying your saved protocol.
  • Each article will display the AI’s inclusion/exclusion decision along with a rationale and PICOS.
  • Human reviewers (Project Owner/Lead Reviewer) can view, verify, or override AI decisions at any point.
Reviewing AI Decisions
Even with AI-only review:
  • You can override any AI decision using the Quality Check (QC) functionality.
  • Use filters (e.g., Included, Excluded) to manually spot-check decisions.
  • Run AI Performance Analysis on a sample set to validate accuracy before scaling.
Best Practices
  • Start with a representative sample (100–200 citations) to check decision match rate and recall.
  • Use Protocol Text Review to optimise your inclusion/exclusion logic for AI (Refer to the help article here).
  • Rerun AI for all once Protocol is optimised.
Note: While AI features can assist and speed up the review process, users should be aware that large language models (LLMs) may produce incomplete or incorrect results. Clear and well-defined protocols are essential for reliable AI support. All AI outputs should be carefully reviewed, and the final judgment and decision-making responsibility always rests with human reviewers.

FAQs
Q: Can I still switch to a dual-review setup later?
Yes. You can update your project settings to include human reviewers at any time.

Q: Will I be able to track what AI included or excluded?
Absolutely. All decisions made by AI are logged and the project progress can be tracked from the Statistics section.

Q: Is this available for both Title-Abstract and Full-Text stages?
Yes, once enabled AI will review articles at both stages independently.

Q. If we change the project settings from 1 Human Reviewer to AI as the only Reviewer, will previous decisions be overridden?
No, previous human decisions will remain intact. The review configuration will change going forward.

Need Help?
Feel free to reach out via Live Chat or drop an email at support@easyslr.com.

    • Related Articles

    • List of AI Models Used Across EasySLR

      EasySLR uses purpose-specific GPT models across different review stages to optimise accuracy, performance, and cost efficiency. Each model has been selected based on the complexity and nature of the task it supports, ensuring reliable AI assistance ...

    • How to run AI on the articles that are already screened by Human Reviewers?

      EasySLR allows you to run AI on articles after they’ve been screened by human reviewers. Just follow the steps below to initiate the AI run and compare with the human decisions. If any differences arise, the Conflict Analysis tool helps you ...

    • Comparing AI Assistant and AI Reviewer in EasySLR

      EasySLR utilises advanced artificial intelligence to streamline and enhance the article screening process. Within the platform, two key AI features play pivotal roles: the AI Assistant and the AI Reviewer. While both are designed to enhance ...

    • How to Compare AI vs Human Reviewer Decisions in EasySLR?

      EasySLR allows you to assess the accuracy and reliability of its AI-driven screening by directly comparing AI decisions with those made by human reviewers. This validation step helps you understand how closely the AI aligns with your decision-making ...

    • Using AI as a Second Reviewer in EasySLR

      EasySLR offers an advanced AI-powered second reviewer feature to work alongside human reviewers, revolutionizing the way literature reviews are conducted. This powerful combination ensures a comprehensive and thorough review process, blending the ...