LitFlow

What LitFlow is

LitFlow is an AI-augmented workspace for systematic literature reviews, covering search, screening, extraction, synthesis, and reporting. Search tools include database search, snowballing, and AI-generated synonyms. During screening, AI proposes criterion-by-criterion verdicts with confidence scores, reasons, and links to source passages, while researchers make the decisions. The system records suggestions and human decisions with timestamps, actors, and rationales. Users can create custom extraction schemas with LLM pre-fill and source links, then structure themes on a qualitative coding board. Reports include PRISMA information, Cohen’s κ, and an audit trail in a methods report intended for publication. Users can bring keys for Gemini, Claude, OpenAI, or Mistral, or use open-source models hosted by the University of Münster. The project is operated by the university’s research team in Münster, Germany. Its hosted closed alpha runs on university infrastructure in the EU, and maintainers approve new cohort members. Academic use is free; no commercial tier is listed.