Move from a candidate paper set to inclusion and exclusion decisions with AI recommendations you can review, override, and audit before the synthesis starts.
Editable workflow
Each stage stays visible, so you can revise the scope or evidence choices before generating again.
Search and retrieve a deduplicated candidate set.
Review relevance scores and AI screening recommendations.
Confirm inclusion, record exclusions, resolve uncertain papers.
Pass only the included set to extraction and synthesis.
LitSynth treats AI as support for a review process. You keep control of which papers enter the evidence set and which claims need another check.
Score retrieved papers for relevance against your review question.
Receive include and exclude recommendations with stated reasons.
Confirm, override, or defer decisions on borderline papers.
Export a screening record that survives later inspection.
AI can score relevance and recommend include or exclude decisions with reasons, which removes most of the repetitive reading. LitSynth keeps those recommendations visible and lets you confirm or override each one, so the final decision and the responsibility stay with the reviewer.
Dedicated screening tools stop at the screening decision. LitSynth carries the screened set directly into evidence extraction and a cited synthesis, so you do not export and re-import between tools.
Yes. Each recommendation carries a stated reason tied to your eligibility criteria, and exclusions remain visible in the screening record rather than disappearing from the set.
PRISMA requires transparent reporting of how screening was done, not a specific tool. You should document AI assistance in your methods and retain human verification, which LitSynth supports by keeping decisions inspectable.
Search papers, screen the evidence, generate a cited draft, and return to earlier decisions whenever the scope needs to change.
Start your review