EST. 2025 · University of Münster · Chair of Business Process Management

A research project, born from real friction.

LitFlow began with the friction of running systematic literature reviews — and the unresolved question of how, and whether, LLMs can and should be used in that work.

Mission

Three principles.

01

Show your work

Every AI suggestion carries its confidence, its justification, and its source.

02

Recommend, don't decide

The system is a collaborator, not an autonomous agent. Inclusion, exclusion and interpretation remain decisions belonging to the human reviewer — always.

03

Build in the open

Code, prompts, evaluation data and roadmap are public.

The story

Four iterations.

LitFlow is built in echeloned cycles — each iteration framed, designed and evaluated before the next.

Iteration 01

Problem scoping

Framing the gap: SLR tools cover parts of the workflow, but transparency and configurability of AI support are missing.

Iteration 02

Survey

A survey of 178 researchers on SLR tooling and unmet needs grounds the design requirements.

Iteration 03

Web platform

The end-to-end LitFlow platform — search, screen, extract and report in one document model.

Iteration 04

Formative evaluation

A think-aloud evaluation with five information systems researchers across the full workflow.

Iteration dates to be confirmed before launch.

Affiliation

Where LitFlow sits.

Department

Information Systems · University of Münster

University

University of Münster, Germany

In the literature

Read further.

The DESRIST 2026 paperThe peer-reviewed paper behind LitFlow.Field notesThe ongoing record of what we're learning.
Get in touch

How to reach the project.

Join the alpha →