From research question to published evidence.

AutoEvidence handles the screening, extraction, and statistical synthesis that consumes months of researcher time — so you can focus on the science.

10×
faster than manual screening
98%
AI screening accuracy
40h
saved per review on average
PRISMA
compliant reports
See it work

Three AI reviewers screen every abstract

Claude, GPT-4o, and Gemini independently vote include / exclude on each title and abstract. Unanimous decisions auto-route. Disagreements surface for human review with Cohen's κ inter-rater reliability so you know exactly where to focus.

Claude Opus·GPT-4o·Gemini
Cohen's κ = 0.92 · Almost perfect
AutoEvidence · Screening
3 / 199 screened · live
3
Screened
2
Included
2
Excluded
1
Borderline
  • Faricimab vs Aflibercept in Treatment-Naïve Neovascular AMD: 12-Month Results of the TENAYA Trial
    Khanani A.M., Guymer R.H., et al. · Ophthalmology (2026)
    include
    Cinclude95%Ginclude92%Gminclude90%
  • Real-World Six-Month Outcomes After Switching from Aflibercept 2 mg to 8 mg
    Kindo H., Hosokawa M., et al. · Japanese Journal of Ophthalmology (2026)
    exclude
    Cexclude95%Gexclude90%Gmexclude95%
  • A Phase III Randomized Trial Comparing ZRC-3285 vs Eylea® in Wet AMD
    Bansal M., Singh P., et al. · Ophthalmology and Therapy (2026)
    include
    Cinclude95%Ginclude95%Gminclude95%
  • Cost-Utility Analysis of Faricimab vs Aflibercept in nAMD
    Baljoon A., Diaby V., et al. · PharmacoEconomics — Open (2026)
    exclude
    Cexclude90%Gexclude95%Gmexclude95%
  • Twelve-Month Outcomes of Aflibercept 8 mg in Treatment-Naïve Diabetic Macular Edema
    Spindler J., Artemiev D., et al. · Ophthalmology Science (2026)
    Human review
    Cinclude80%Guncertain60%Gmexclude70%
Agreement rate93%

Sample data from a real ophthalmology meta-analysis. Live screening processes thousands of records in minutes.

Everything a systematic review demands.

A complete evidence-synthesis workflow from PICO to publication, in one platform.

Claude · GPT-5 · Gemini

Dual-pass AI screening

Claude AI screens every abstract twice and flags borderline cases. Cohen's κ inter-rater reliability scores tell you exactly where to focus.

Forest · Funnel · GRADE

Meta-analysis engine

Random- and fixed-effects models with forest plots, funnel plots, and I² heterogeneity — computed in-platform, exportable to your manuscript.

4 databases

Multi-database search

PubMed, Embase, Cochrane, and ClinicalTrials.gov queried simultaneously with one PICO.

Pre-screening

Vector deduplication

Fuzzy matching plus embedding similarity eliminate duplicates before screening.

RoB2 · ROBINS-I

Risk of bias

RoB2 and ROBINS-I frameworks with auto-generated GRADE evidence tables.

PRISMA-P

Protocol generation

PRISMA-P compliant protocols with eligibility criteria and PROSPERO-ready output.

PRISMA flow

Full-text review

Structured screening with exclusion reasons mapped to PRISMA flow categories.

JSON · CSV · RIS · BibTeX

PRISMA 2020 reporting

Auto-generated PRISMA flow diagrams and full reports — exportable as JSON, CSV, RIS, BibTeX, or SVG.

From question to evidence in five steps.

A guided workflow that matches how systematic reviews are actually conducted.

  1. 01

    Define your PICO

    Set population, intervention, comparator, and outcome with guided templates.

  2. 02

    Search & import

    Query multiple databases. We deduplicate and import in seconds.

  3. 03

    AI screens abstracts

    Claude processes thousands of abstracts. You review only the borderlines.

  4. 04

    Extract & assess

    Structured data extraction and automated risk of bias assessment.

  5. 05

    Meta-analyse & report

    Statistical synthesis, visualisations, and PRISMA-compliant export.