Running a review
Every stage of a systematic review, from the protocol to extraction.
- Config: the protocol of your reviewEverything a review's Config tab holds, from the question and numbered criteria to blind mode, extraction mode and the autopilot's rules, and why each matters for the paper.
- Importing search resultsOne file per database search, with its source, date and search string. The formats that work, and how the imports become your PRISMA-S search log.
- Searching the databases from the appWrite the search string once; the app writes it for each database, counts the hits, retrieves the records and logs every search for the PRISMA-S appendix. …
- Finding and merging duplicatesDuplicates are found by DOI, PMID and normalised titles. Exact groups merge in one click; likely ones are yours to judge.
- Title and abstract screeningTwo people judge every record independently. The keys, the highlights, the verdicts on each criterion, notes and labels, and what blind mode hides.
- Conflicts and discussionsRecords where independent votes differ get a discussion thread. AI co-authors can reply and may change their vote; an owner or co-author resolves.
- Full text: finding PDFs and assessing reportsOpen-access PDFs are found for you; you upload the rest or mark a report as not retrieved. Then each report is assessed against every criterion, and every exclusion needs a reason.
- Data extractionA form built from templates, by hand or proposed by the AI; manual, AI pre-fill or AI automatic modes; quotes checked against the study; a compare view for several extractors; tabl …
- Related work: comparing prior surveysFind prior surveys, rate each on your review's dimensions, and get the justification table that shows what your review adds.
- ExportsEverything a journal, a co-author or your own records may need: records with every vote, references, extraction data and the LaTeX project.
- Clone, lock, archive and delete a reviewThe four actions on a review's card. Archive a review once its paper is published: it is kept for good, read-only, with the publication's details and a ready BibTeX entry.
- Agreement and Cohen's kappaHow the app measures how well screeners agree beyond chance, which pairs it reports, and why discussions and resolutions do not change it.