Custom AI reviewer agents for research papers

A custom reviewer agent is a set of instructions you write, or paste, that tells PerfectPaper what to look for in your manuscript beyond its standing specialist review. You can add up to three to any review. Each takes a name, instructions up to 6,000 characters, a work type, a skill level, and an optional selection of tools: web search, scholarly search, code execution, and vision for reading figures.

The standing team covers what every paper needs — structure, language, numeric integrity, figures, tables, citations, prior work, logic, methodology, statistics, causal inference, journal fit. Custom agents exist for what only your subfield needs, and every field has conventions that a generalist reviewer does not know to check.

Prebuilt agent briefs by field

Genomics, epigenetics and metabolism — multiple testing and enrichment, data availability and accessions, batch effects, metabolomics reporting, variant nomenclature.

Preclinical cancer research — pseudoreplication and unit of analysis, in vivo rigour, flow cytometry reporting, image quantification, model relevance.

Clinical trials and experimental therapeutics — response criteria, early-phase safety, registration and endpoints, synergy claims, translational dose.

Epidemiology and population science — health equity reporting, competing risks, registry data validity, causal language, qualitative rigour.

Agents that suit any field

Ethics, consent and data sharing — approval statements, consent scope for data sharing, de-identification, data management plan compliance.

Overclaim check — the distance between what was shown and what the discussion says, tuned to translational overreach.

Study section lens — reads the manuscript the way a grant reviewer scoring significance and innovation would, which is a different job from peer review.

Writing your own

The prebuilt briefs are complete and can be pasted unchanged, but the most valuable agent is usually one you write for a convention you have been burned by before. How to write a custom reviewer agent covers the structure that works, the instructions worth including, and the ones that make an agent worse.

PerfectPaper can also propose an agent for your specific paper from its title and abstract, which you can then edit before running.

Why three

Three slots is a deliberate limit rather than a tier. An agent asked to check everything checks nothing in particular, and the briefs that produce useful findings are narrow ones. Three narrow agents outperform one broad agent by a wide margin, and the constraint pushes toward the narrow form.

Review my manuscript

Frequently asked questions

What is a custom AI reviewer agent?

A set of instructions you supply that PerfectPaper runs against your manuscript alongside its standing specialist team. You give it a name, instructions, a work type, a skill level, and optional tools. PerfectPaper supplies the review contract and output format, so the brief describes what to look for rather than how to report it.

How many custom agents can I add?

Three per review. They run alongside the built-in specialists rather than replacing any of them.

How long can the instructions be?

Up to 6,000 characters. Every prebuilt brief on this site fits comfortably inside that, with room to add your own items.

Can a custom agent search the literature or run calculations?

Yes. Each agent can be given web search, scholarly search, code execution, or vision for reading figures. Give tools only where the task needs them — a checking task that reads only the manuscript is usually more reliable without them.

Do custom agents cost extra?

No. They run as part of the review rather than as a separate charge, so adding three costs the same as adding none.

Will a custom agent duplicate the built-in review?

It can, which is why every brief on this site states what the standing team already covers. The best use of a slot is a convention specific to your assay, design or field.