Systematic reviews, from PICO question to forest plot.

Collie brings search, blind dual screening, extraction, risk of bias, meta-analysis in R and PRISMA 2020 onto one desk. AI suggests, with reasons. You decide.

Free to run on your own computer. No credit card.

Title and abstract screening Blind mode

sample record

Search inside Collie

    Strategy translated, results imported from

      Statistics in

        Nine steps. One trail.

        Each step hands off to the next with no spreadsheet exports and no copy-paste, and with an audit trail of who decided what.

        Built for the rigor your committee and peer reviewers expect.

        The methods described in the Cochrane Handbook, already in the right place in the workflow.

        PICO search that becomes a boolean string

        Build population, intervention and outcome blocks with MeSH terms and synonyms. Collie writes the syntax for each database, applies filters such as the Cochrane HSSS and shows the count before you import.

        • Validation against studies you already know should appear
        • Eight import formats and deduplication in the same panel
        • Forward and backward citation searching through the graph
        PubMed, 1,248 results
        ("Diabetes Mellitus, Type 2"[Mesh] OR "type 2 diabetes"[tiab] OR T2DM[tiab])
        AND
        ("Resistance Training"[Mesh] OR "strength training"[tiab] OR "weight lifting"[tiab])
        AND
        ("Glycated Hemoglobin"[Mesh] OR HbA1c[tiab])
        AND
        (randomized controlled trial[pt] OR randomi*[tiab])
        PopulationInterventionOutcomeDesign filter

        Meta-analysis in R, without leaving the review

        Extracted data feeds the {meta} package directly: binary, continuous, generic, proportion and correlation, with random effects, subgroups, leave-one-out, funnel plots and trim-and-fill.

        • A reproducible analysis.R to attach to your manuscript
        • Bayesian models when the question calls for them
        • GRADE per outcome with a Summary of Findings table
        Mean difference in HbA1c (%), random effects. Illustrative data.

        Blind dual screening

        Reviewers vote without seeing each other's votes. Conflicts are resolved by consensus or majority, and Cohen's kappa is calculated for you.

        Risk of bias with the right tools

        RoB 2, ROBINS-I, QUADAS-2, Newcastle-Ottawa, QUIPS and JBI, with robvis-style figures.

        A PRISMA 2020 diagram that fills itself in

        The flow diagram follows your real decisions, and the 27-item checklist shows what is still missing.

        1. 1,248 records identified
        2. 1,016 after removing duplicates
        3. 87 full texts assessed
        4. 14 studies included

        AI suggests. You decide.

        The assisted reviewer reads each record against your criteria and explains its suggestion criterion by criterion. Nothing is saved as a decision until a person accepts it, and the audit trail separates what came from people and what came from the machine.

        Collie
        Justifies with the I1, E2… criteria you wrote
        Generic chat
        Answers from whatever it learned on the internet
        Collie
        Extraction with a quote checked against the PDF
        Generic chat
        Numbers without the page they came from

        Assisted reviewer

        Suggests include, moderate confidence

        • I1 Adults with T2D “patients aged 40 to 65 with type 2 diabetes”
        • I2 Supervised resistance training “3 weekly sessions with a physiotherapist”
        • I3 HbA1c outcome “change in HbA1c at 12 weeks”
        • E1 Non-randomized design Allocation described only in the full text
        terminal

        Take your review to the agent you already use.

        Collie ships an MCP server that connects in one click to Claude Code, Codex, Gemini CLI and Cursor. The agent reads and writes the review under the same rules as the app: suggestions stay separate and wait for human approval.

        • Plugin with 13 skills, 8 agents and 4 hooks
        • Connects through your account, no keys to copy

        6 built-in search databases

        6 risk of bias tools

        27 PRISMA items with automatic status

        3 languages: English, Portuguese and Spanish

        5 themes, including a color-blind mode

        Start free. Upgrade when the review gets serious.

        Using Collie in your browser is free forever. Paid plans add the cloud, collaborators and built-in AI.

        Prices in US dollars. Cancel anytime; your reviews stay exportable.

        Frequently asked questions

        Everything you need to know before your first review.

        Does my data leave my computer?

        Not in the local version. Everything lives in a SQLite file on your machine. The cloud only comes in if you choose a plan with online collaboration.

        Can the AI include or exclude studies on its own?

        No. Suggestions and extractions are stored separately, with their reasons, until someone on the team accepts them. The audit trail records which decisions were human and which were suggestions.

        Do I need to know how to code in R?

        No. Collie runs R behind the scenes and shows the forest plot, funnel plot and tables. If you want, download analysis.R and reproduce everything in RStudio.

        Can I bring in a review I started in another tool?

        Yes. Collie imports RIS, NBIB, BibTeX, CSV and other common export formats, and detects duplicates on the way in.

        Is it suitable for a thesis or dissertation?

        Yes. The workflow follows the Cochrane Handbook and produces the PRISMA 2020 diagram and checklist that committees and journals ask for.

        Can I register my protocol on PROSPERO from Collie?

        Not yet. It is on our roadmap. For now you build the PICO question and criteria in Collie and copy them into the PROSPERO form.

        Your next review starts with a question.

        Install, create the review and write your PICO. Collie keeps the trail all the way to PRISMA.