RobotReviewer vs Systematicly

RobotReviewer analyzes clinical trial reports by annotating PDFs with PICO characteristics and likely bias assessments using the Cochrane Risk of Bias tool. Uploading PDFs on the website extracts key data and presents a summary table. Its REST API can process groups of clinical trial reports to synthesize results across trials. The project is open source under GNU GPL version 3.0 and is free to use. It can run locally as Docker services, with a web app and API server exposed on local ports. The self-hosted processing setup uses Grobid, RabbitMQ, Celery, and SciBERT through bert-as-a-service. Docker instructions cover GPU use, and the worker can also run CPU-only. Manual setup calls for Python 3.6, TensorFlow 1.12.0, and the associated processing services. Installation is documented as tested on Ubuntu and Mac OS; Windows works with substantial installation difficulty. Maintainers ask users to cite the 2017 ACL paper and invite questions by email, including requests for help integrating RobotReviewer into other software.

Systematicly is a web-based research platform for systematic reviews, primary research, ethics applications and research proposals. It can analyze a topic using PICO, PECO or SPIDER frameworks and produce Boolean searches for databases including PubMed, Scopus, Web of Science, ERIC and PsycINFO. Reviewers can screen titles and abstracts and upload PDFs for structured field extraction. Analysis options include 1,033 statistical functions, plain-English analysis, meta-analysis, plots, sensitivity analysis and GRADE assessment. The platform lists eight review types, plus publishing tools such as AI-assisted manuscripts and proposals, PRISMA diagrams, journal recommendations and reviewer response letters. It retrieves PDFs automatically from PMC, Unpaywall and EuropePMC, and supports ClinicalTrials.gov imports and several reference formats. The free Explorer plan is limited to three active personal drafts, one lifetime feasibility preview and three lifetime Evidence Answers. Paid one-time options include a single Evidence Answer for $19, paid once and literature review packages from $149, paid once. The security page says user data is not used to train AI models; Anthropic’s commercial API may retain inputs and outputs for up to 30 days for trust and safety monitoring.