AI peer review — editor-ready feedback before you submit

What 'AI peer review' actually means here

AI peer review is an automated first-pass referee report: software reads your full manuscript and returns the same kind of structured, criterion-by-criterion feedback a journal reviewer would — methodology, originality, literature coverage, clarity — before you submit anywhere. It complements human peer review; it does not replace it.

Rather than wrap the whole review in a single LLM prompt, ours decomposes it into 8 specialist agents — Methodology, Formulas & Equations, Originality, Literature Coverage, Reproducibility, Clarity & Language, Figures & Tables, Prior Publication. Every agent except Prior Publication is a language model with its own prompt, written around the reporting standards and venue review conventions of its dimension (CONSORT, STROBE and PRISMA among them); Prior Publication is a database lookup, not a language model.

At inference time, each language-model agent's prompt is seeded with excerpts from real peer reviews in our 69K-review training corpus, retrieved by FTS5 full-text search on that agent's specialty. That is the calibration step: the model doesn't just know 'what a review looks like' in the abstract; it's shown concrete examples of how real reviewers judged the dimension it is judging, every time it runs. The examples are chosen by the agent's specialty, not matched to your manuscript's field.

How the review runs

Submit a PDF or paste a DOI / arXiv ID. The engine fans out in parallel:

• A prior-publication check across CrossRef, PubMed, arXiv, bioRxiv, medRxiv, Europe PMC and Unpaywall, plus our 4.5M-paper local library — all queried in parallel, each capped at 12 seconds.
• Then the specialist agents run in parallel, the language-model agents each against its own prompt; a possible prior publication is flagged in the report, not a reason to stop.
• A synthesis step integrates the specialist reports into a single structured review with an overall score.
• Output is delivered as a readable report and a machine-readable JSON object (for integration into CI or writing tools).

When to use it

The tool is most useful in three situations:

• Pre-submission triage — 15 minutes before you send a draft to a closed journal or conference.
• Revision planning — after you get a R&R from a journal, re-run to see what the 'second reviewer' would flag.
• Self-training — PhD students and early-career researchers use it to internalise what referees look for in their field.

Pricing

Pay-as-you-go credits — you pay per run, not per seat, and there is no subscription. Creating an account is free and comes with 25 credits to start. Pre-Check (acceptance odds for top, mid and open/emerging journals, from the title and abstract) costs 15 credits — enough for the 'should I keep polishing or submit now?' call. The full 8-agent report with per-section feedback, prior-publication evidence, and the JSON export costs 30 credits.

Credits are bought in one-time packs and never expire — no recurring charge.

Frequently asked questions

Related tools

• Research Gap Finder — start earlier in the pipeline — find an open, citable research gap before you write the paper.
• Journal Finder — match your reviewed paper to the right venue — ranked shortlist with predatory-journal flags.
• How long does peer review take? — the real timelines at traditional journals, field by field — and what a 15-minute first pass changes.