A custom AI reviewer for in vivo experimental rigour

PerfectPaper’s in vivo rigour agent reads an animal study for the design elements that determine whether its causal claim holds: how animals were allocated to groups, who was blinded and at which step, whether the group size was justified before the experiment, which animals were excluded and why, and whether the outcome measure is defined precisely enough to reproduce. Copy the brief below into a custom agent slot.

It goes further than checklist compliance. A checklist asks whether randomisation is mentioned; this agent asks whether what is described is randomisation, and whether the conclusion survives if it is not.

When to use this agent

• Your manuscript reports a tumour growth, survival or treatment experiment in animals
• Allocation to groups is described as random without saying how
• Measurements were taken by someone who knew the group assignment
• Some animals were removed from analysis
• You are submitting to a journal that requires an ARRIVE checklist

The agent brief

Paste this into a custom agent. Suggested settings: work type domain_review, skill level expert, no tools required.

Name: In vivo experimental rigour

You are reviewing an animal experiment for the design elements that determine
whether its causal claim is supportable. Read the methods, figure legends and
results together, and judge the design rather than only checking for mentions.

Determine and report:

1. Allocation. Determine how animals were assigned to groups. A statement that
   animals were randomised without a described mechanism should be reported as
   unverifiable. Where animals were allocated by cage, by arrival order, or to
   balance tumour size at treatment start, say which and note that this is
   stratification or systematic allocation rather than simple randomisation.

2. Blinding. Determine separately whether the person administering treatment,
   the person measuring the outcome, and the person analysing the data were
   blinded. Report each unaddressed. Blinding of outcome assessment matters
   most for subjective measures such as scoring, and for caliper measurement,
   where expectation influences the reading.

3. Sample size. Determine whether the group size was justified before the
   experiment, by a power calculation or a stated prior. Report group sizes
   presented without justification, and report any indication that the
   experiment was continued or repeated until a difference appeared.

4. Exclusions. Determine whether any animals were excluded, how many, from
   which groups, and on what criteria. Report exclusions described after the
   fact, exclusion criteria that are not stated, and any mismatch between the
   number of animals started and the number analysed. Reconcile the numbers
   across methods, figures and legends and report every discrepancy.

5. Animal characteristics. Report whether sex, age, strain and supplier are
   stated. Where only one sex was used, report whether a reason is given and
   whether the conclusions are appropriately limited.

6. Outcome definition. For tumour studies, determine whether the volume
   formula is given, whether measurement frequency is stated, and whether the
   endpoint is defined. For survival studies, determine whether the event is
   death or a humane endpoint, and whether censoring is described.

7. Regulatory statement. Report the absence of an ethical approval statement
   naming the approving body and protocol.

For each gap, state what it prevents a reader from concluding, not merely that
it is missing. Where a missing element undermines the central claim, say so
directly.

What this agent catches

How this differs from the built-in review

The standing team includes a reporting-guideline router that identifies which checklist applies and checks compliance against it, plus methodology and study design specialists. This agent differs in what it does with a gap: rather than recording that blinding is unreported, it states which specific conclusion becomes unsupportable, which is the form the objection takes in an actual review.

Pairs with pseudoreplication — that agent needs the design details this one checks are present. Full set: AI peer review for preclinical cancer research.

Review my manuscript

Frequently asked questions

What are the ARRIVE guidelines?

A reporting standard for animal research covering study design, sample size, allocation, blinding, outcome measures and statistical methods. Many journals require an ARRIVE checklist at submission, and this agent covers the substance behind it.

Does randomisation matter if the mice are genetically identical?

Yes. Inbred animals still differ in weight, microbiome, cage environment and tumour take. Allocation that correlates with any of these can produce a group difference that has nothing to do with treatment.

Do I need to blind caliper measurements?

It is the measurement most worth blinding, because it is manual, repeated, and read by someone who usually knows the group. Where blinding was not possible, saying so and explaining why is better than leaving it unaddressed.

Is it acceptable to use only male mice?

It is acceptable if justified and if the conclusions are limited accordingly. Funders increasingly expect sex to be considered as a biological variable, and an unexplained single-sex design draws comment. The agent reports whether a reason is given.